INDEX

Explanations

trigger words related to drugs and substances

oai_token-act-pair · gpt-3.5-turbo

terms related to health, drugs, and nutrition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Daylight

-0.66

 Solitaire

-0.59

OTOS

-0.56

 Sirius

-0.55

UTF

-0.54

 Polaris

-0.53

nih

-0.53

 Bronze

-0.52

doi

-0.52

 TOUR

-0.52

POSITIVE LOGITS

roying

1.09

itored

1.09

renched

1.00

tenance

0.93

quartered

0.93

ielding

0.92

avored

0.89

ASED

0.88

rived

0.87

ained

0.86

Activations Density 0.108%

trigger words related to drugs and substances

terms related to health, drugs, and nutrition

No Comments

No Known Activations