INDEX

Explanations

phrases related to fear

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

issance

-0.64

abase

-0.63

eret

-0.63

iary

-0.61

 converter

-0.61

ributes

-0.59

ellery

-0.59

anmar

-0.59

erent

-0.59

estone

-0.59

POSITIVE LOGITS

 heights

0.88

 repr

0.73

 ghosts

0.69

 retribution

0.64

 retaliation

0.63

 snakes

0.62

 drowning

0.61

 losing

0.60

ger

0.57

Activations Density 16.883%

phrases related to fear

No Comments

No Known Activations