INDEX

Explanations

references to political events, ideologically charged topics, and historical context

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

 guiActiveUnfocused

-0.58

 Eighth

-0.57

duc

-0.56

hips

-0.53

 Guinea

-0.53

natureconservancy

-0.51

"],"

-0.49

 Guant

-0.49

âĦ¢:

-0.48

 excess

-0.48

POSITIVE LOGITS

self

0.97

unes

0.88

zbollah

0.88

achi

0.83

iner

0.83

amar

0.80

'll

0.78

zik

0.77

chy

0.76

miah

0.75

Activations Density 10.967%

references to political events, ideologically charged topics, and historical context

No Comments

No Known Activations