INDEX

Explanations

scientific research terms related to establishing connections or relationships between different factors

oai_token-act-pair · gpt-3.5-turbo

terms related to associations and connections between different variables or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

disk

-0.68

STRUCT

-0.68

 pomp

-0.64

ger

-0.64

gem

-0.62

sk

-0.62

quer

-0.61

 helicop

-0.61

 gall

-0.61

phia

-0.60

POSITIVE LOGITS

 linking

0.99

between

0.82

 Between

0.80

 link

0.80

alogy

0.79

 Attribution

0.78

 between

0.77

 linkage

0.77

uality

0.76

 causation

0.76

Activations Density 0.068%

scientific research terms related to establishing connections or relationships between different factors

terms related to associations and connections between different variables or concepts

No Comments

No Known Activations