INDEX

Explanations

phrases related to extreme situations or conditions

oai_token-act-pair · gpt-3.5-turbo

terms associated with evaluation, assessment, or comparison

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

 Citation

-0.71

 Summit

-0.68

Jav

-0.67

 Mirage

-0.66

 Chronicles

-0.65

 Cobra

-0.65

DV

-0.64

 CCTV

-0.64

KC

-0.63

 Monetary

-0.62

POSITIVE LOGITS

enos

0.96

ifiable

0.95

isable

0.93

ictive

0.89

ctic

0.89

erous

0.88

achable

0.88

rescent

0.87

iable

0.86

eny

0.85

Activations Density 0.572%

phrases related to extreme situations or conditions

terms associated with evaluation, assessment, or comparison

No Comments

No Known Activations