INDEX

Explanations

mentions of dramatic or intriguing developments or situations

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

velt

-0.73

amiya

-0.64

 Britann

-0.64

 Examiner

-0.58

heid

-0.57

iege

-0.57

 Costume

-0.56

 hypothesis

-0.54

isse

-0.54

orney

-0.53

POSITIVE LOGITS

rid

1.02

cloneembedreportprint

0.88

 progressively

0.81

 underway

0.75

tin

0.74

TING

0.71

aways

0.71

bog

0.70

 louder

0.70

 traction

0.70

Activations Density 6.705%

mentions of dramatic or intriguing developments or situations

No Comments

No Known Activations