INDEX

Explanations

instances of words related to situations or events that may cause concerns or discussions

oai_token-act-pair · gpt-3.5-turbo

terms related to safety and risk events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ģĸ

-0.98

Adapt

-0.90

ahime

-0.85

 guiName

-0.83

obook

-0.79

derived

-0.78

ESE

-0.76

ranch

-0.73

thood

-0.72

abase

-0.72

POSITIVE LOGITS

 bruises

1.43

 gunshots

1.28

 gunfire

1.27

 tears

1.24

 yelling

1.24

 explosions

1.18

 noise

1.17

 cursing

1.17

 stares

1.16

 distractions

1.15

Activations Density 0.322%

instances of words related to situations or events that may cause concerns or discussions

terms related to safety and risk events

No Comments

No Known Activations