INDEX

Explanations

keywords related to leaving or exiting

oai_token-act-pair · gpt-3.5-turbo

terms related to the concepts of withdrawal and escape

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

nan

-0.71

enegger

-0.70

Cola

-0.69

organic

-0.63

illac

-0.62

 nutrit

-0.62

geries

-0.62

aughtered

-0.61

eyes

-0.60

 Parenthood

-0.59

POSITIVE LOGITS

ary

0.81

 ceremony

0.79

 Syndrome

0.78

 ceremonies

0.76

 rite

0.76

 syndrome

0.75

 clause

0.74

 route

0.74

ment

0.73

 routes

0.73

Activations Density 0.256%

keywords related to leaving or exiting

terms related to the concepts of withdrawal and escape

No Comments

No Known Activations