INDEX

Explanations

phrases related to food items, especially sandwiches

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

runner

-0.92

fee

-0.83

uno

-0.81

Reply

-0.81

lists

-0.75

jury

-0.74

gin

-0.73

cv

-0.73

uria

-0.71

-0.69

POSITIVE LOGITS

wich

1.03

insula

0.94

inant

0.89

berman

0.85

abwe

0.84

awks

0.79

nikov

0.77

reet

0.76

olson

0.75

awk

0.75

Activations Density 6.229%

phrases related to food items, especially sandwiches

No Comments

No Known Activations