INDEX

Explanations

text related to various topics such as science, history, culture, and politics

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 inactive

-0.63

 wording

-0.56

 interviewer

-0.56

itely

-0.55

 portions

-0.55

 cowork

-0.54

idav

-0.54

 cutoff

-0.54

wcsstore

-0.54

 saline

-0.54

POSITIVE LOGITS

ankind

0.84

thood

0.82

manship

0.81

 =================================

0.80

smanship

0.75

utics

0.73

anship

0.71

Reviewer

0.70

 wherein

0.67

isine

0.65

Activations Density 19.438%

text related to various topics such as science, history, culture, and politics

No Comments

No Known Activations