INDEX

Explanations

legal and procedural terms

oai_token-act-pair · gpt-3.5-turbo

numerical data and legal references

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

byn

-0.81

orld

-0.75

emale

-0.72

trl

-0.71

krit

-0.70

ocre

-0.69

avid

-0.69

enes

-0.69

avorite

-0.69

outube

-0.69

POSITIVE LOGITS

APTER

1.09

Â§

1.08

 Notwithstanding

1.00

 subparagraph

0.96

``(

0.96

 subsection

0.94

.--

0.92

 Appropri

0.91

.''.

0.90

 enactment

0.90

Activations Density 0.291%

legal and procedural terms

numerical data and legal references

No Comments

No Known Activations