INDEX

Explanations

rules and guidelines

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

NetMessage

-0.93

 ILCS

-0.82

needed

-0.81

ayson

-0.76

-0.75

sites

-0.75

Task

-0.75

auga

-0.73

\<

-0.72

 âĢº

-0.71

POSITIVE LOGITS

 physics

0.93

 therm

0.91

 propri

0.84

icial

0.77

 thumb

0.76

clud

0.75

 logic

0.75

glers

0.75

 evolution

0.74

 relativity

0.73

Activations Density 18.251%

rules and guidelines

No Comments

No Known Activations