INDEX

Explanations

words related to wanting, desires, and intentions

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

manship

-0.63

erver

-0.62

mans

-0.61

iop

-0.59

inas

-0.57

lish

-0.57

 Â®

-0.57

minus

-0.57

aka

-0.57

wikipedia

-0.56

POSITIVE LOGITS

 warr

0.63

teness

0.63

 permission

0.61

rison

0.59

 revenge

0.56

nesday

0.55

 millenn

0.55

reprene

0.53

to

0.53

RAG

0.53

Activations Density 5.984%

words related to wanting, desires, and intentions

No Comments

No Known Activations