INDEX

Explanations

people's names and organizations related to political discussions or conflicts

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

paio

-0.71

shock

-0.69

sed

-0.69

fman

-0.69

ny

-0.69

fit

-0.69

thodox

-0.68

orate

-0.67

mosp

-0.66

iosity

-0.66

POSITIVE LOGITS

emonium

0.68

rhy

0.68

 Helpful

0.66

 PsyNet

0.65

enance

0.61

 Plaza

0.58

 Markets

0.56

CBO

0.55

 Hots

0.55

Fas

0.55

Activations Density 8.862%

people's names and organizations related to political discussions or conflicts

No Comments

No Known Activations