INDEX

Explanations

mentions or discussions of revisions or changes

oai_token-act-pair · gpt-3.5-turbo

words related to legal and procedural changes or revisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Mellon

-0.73

ech

-0.73

asia

-0.72

Phones

-0.69

Craft

-0.65

Â¯Â¯

-0.64

 charism

-0.62

 Winged

-0.62

riel

-0.62

 overfl

-0.61

POSITIVE LOGITS

 revision

0.82

 guiActiveUn

0.81

itized

0.72

lator

0.72

 Revision

0.71

 synopsis

0.70

 revisions

0.68

dated

0.68

 formulations

0.67

 retrospect

0.67

Activations Density 0.031%

mentions or discussions of revisions or changes

words related to legal and procedural changes or revisions

No Comments

No Known Activations