INDEX

Explanations

scientific terms or abbreviations commonly found in research papers

oai_token-act-pair · gpt-3.5-turbo

instances of specific scientific or mathematical symbols and notations

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

 Affect

-0.69

 Regulations

-0.64

RTX

-0.63

 à¨

-0.63

 afore

-0.62

 Hass

-0.62

 Deliver

-0.61

 Hoover

-0.61

 behavi

-0.60

 association

-0.59

POSITIVE LOGITS

undred

0.90

bps

0.87

imore

0.83

racuse

0.83

0.82

0.81

0.80

0.79

Activations Density 0.090%

scientific terms or abbreviations commonly found in research papers

instances of specific scientific or mathematical symbols and notations

No Comments

No Known Activations