INDEX

Explanations

mentions of blocking or being blocked

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

lli

-0.79

mble

-0.78

llers

-0.77

gow

-0.75

brates

-0.73

rious

-0.71

ller

-0.70

elt

-0.68

pter

-0.68

enture

-0.67

POSITIVE LOGITS

buster

0.94

busters

0.93

 blocking

0.88

aded

0.85

quote

0.85

ades

0.81

ading

0.77

picking

0.76

 obstruct

0.73

 blockade

0.73

Activations Density 9.840%

mentions of blocking or being blocked

No Comments

No Known Activations