INDEX

Explanations

quotes where the word "well" is used in a neutral or positive context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endants

-0.74

endant

-0.66

venants

-0.65

ourse

-0.65

etitive

-0.64

lete

-0.63

cies

-0.62

mination

-0.61

BIL

-0.61

ues

-0.61

POSITIVE LOGITS

 yeah

0.80

uh

0.76

 blah

0.68

whatever

0.66

yes

0.65

 maybe

0.65

 Wait

0.64

 fart

0.62

etc

0.61

 Euph

0.61

Activations Density 10.647%

quotes where the word "well" is used in a neutral or positive context

No Comments

No Known Activations