INDEX

Explanations

the word "literally" in sentences

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

IFrame

Link

Negative Logits

ramid

-1.03

icipated

-1.00

iem

-1.00

eway

-0.93

ies

-0.90

sonian

-0.90

tein

-0.90

arent

-0.89

winner

-0.89

akers

-0.87

POSITIVE LOGITS

rely

0.87

 speaking

0.82

wed

0.82

staking

0.81

ãĤ§

0.80

ADRA

0.79

ä»£

0.78

UNCH

0.78

 punch

0.77

TY

0.76

Activations Density 0.421%

the word "literally" in sentences

No Known Activations