INDEX

Explanations

quotes from individuals in a textual 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

etheless

-0.89

spir

-0.67

 neighb

-0.64

erity

-0.64

thur

-0.64

rul

-0.63

 tiss

-0.60

 interfered

-0.60

cffffcc

-0.60

mol

-0.58

POSITIVE LOGITS

Sgt

0.72

 Diane

0.71

 Vick

0.68

 Mike

0.68

 Geoff

0.68

 Dawn

0.66

 Chris

0.65

 Andy

0.63

 chuck

0.62

 Sergeant

0.62

Activations Density 8.405%

quotes from individuals in a textual context

No Comments

No Known Activations