INDEX

Explanations

statements indicating the presence or absence of evidence or suggestions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a lack of evidence or denial of claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cellaneous

-0.70

ione

-0.67

è»

-0.65

Boss

-0.65

Dialogue

-0.63

izont

-0.63

inic

-0.62

 Pieces

-0.61

feet

-0.61

 largeDownload

-0.61

POSITIVE LOGITS

 anymore

1.05

 slightest

0.91

 anyone

0.86

 bothered

0.84

 contradicts

0.84

 whatsoever

0.82

 justifies

0.81

 anybody

0.79

 anything

0.77

 bothers

0.76

Activations Density 0.158%

statements indicating the presence or absence of evidence or suggestions

phrases indicating a lack of evidence or denial of claims

No Comments

No Known Activations