INDEX

Explanations

occurrences of the word 'but'

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

selage

-0.97

natureconservancy

-0.83

otton

-0.75

lf

-0.74

pload

-0.72

ãģķ

-0.72

gee

-0.72

pron

-0.70

 prope

-0.70

 Galile

-0.70

POSITIVE LOGITS

antes

1.01

ante

0.95

aneously

0.82

INGTON

0.79

interstitial

0.77

 Shots

0.76

onement

0.74

tered

0.73

iary

0.73

inct

0.73

Activations Density 0.114%

occurrences of the word 'but'

No Comments

No Known Activations