INDEX

Explanations

expressions of belief, emotion, and judgement related to actions or decisions

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to beliefs and perceptions of danger or risks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ´ãĥ³

-0.76

hoff

-0.74

atche

-0.71

summary

-0.69

 Quote

-0.67

yna

-0.66

ï¸

-0.64

yan

-0.64

jri

-0.64

ussion

-0.64

POSITIVE LOGITS

 they

0.97

 otherwise

0.88

lessly

0.86

 insufficient

0.85

 wrongdoing

0.84

phas

0.81

ingly

0.79

 THEY

0.78

 defective

0.76

 inadequate

0.74

Activations Density 0.266%

expressions of belief, emotion, and judgement related to actions or decisions

words and phrases related to beliefs and perceptions of danger or risks

No Comments

No Known Activations