INDEX

Explanations

technical terms related to data analysis and research, most notably "Analyzer" and "Analytical Engine"

oai_token-act-pair · gpt-3.5-turbo

references to analysis and analytical tools 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

IELD

-0.71

guard

-0.69

 Tales

-0.66

 Cthulhu

-0.66

 goodbye

-0.63

 Toast

-0.63

 Leilan

-0.62

AFTA

-0.62

 Legends

-0.61

guards

-0.60

POSITIVE LOGITS

tical

1.16

sts

1.15

tics

0.99

zes

0.93

berus

0.91

cture

0.90

iqu

0.89

alyses

0.89

ctions

0.88

 analy

0.88

Activations Density 0.017%

technical terms related to data analysis and research, most notably "Analyzer" and "Analytical Engine"

references to analysis and analytical tools or concepts

No Comments

No Known Activations