INDEX

Explanations

references to statements of fact or events

oai_token-act-pair · gpt-3.5-turbo

statements related to emotional or social dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yip

-0.76

hovah

-0.76

ggles

-0.73

ebin

-0.71

 awaits

-0.67

 expires

-0.67

ctuary

-0.64

 prosec

-0.61

habi

-0.61

scribe

-0.60

POSITIVE LOGITS

 lacked

1.00

 mattered

0.92

 tended

0.90

Was

0.88

 knew

0.83

 remained

0.82

 hadn

0.81

 didn

0.80

didn

0.79

had

0.76

Activations Density 1.500%

references to statements of fact or events

statements related to emotional or social dilemmas

No Comments

No Known Activations