INDEX

Explanations

phrases related to political and social issues

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

rex

-0.70

seless

-0.69

cheon

-0.57

ews

-0.57

ward

-0.56

 eliminating

-0.55

oute

-0.55

tube

-0.55

plex

-0.55

 mosaic

-0.55

POSITIVE LOGITS

THING

1.43

WHERE

1.13

ONE

0.94

thin

0.93

body

0.93

where

0.91

how

0.90

place

0.88

MORE

0.83

ones

0.82

Activations Density 9.938%

phrases related to political and social issues

No Comments

No Known Activations