INDEX

Explanations

phrases related to concealed or hidden actions or attributes within a context

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

cca

-0.81

 VIDEOS

-0.76

enegger

-0.74

itivity

-0.73

 Reincarn

-0.72

IONS

-0.71

plex

-0.69

Cth

-0.69

nesday

-0.68

Dial

-0.68

POSITIVE LOGITS

 sources

0.95

 vantage

0.83

 Vend

0.82

 perspective

0.74

 vendors

0.73

 perspectives

0.73

ratch

0.72

animate

0.71

 angles

0.71

 quarters

0.70

Activations Density 0.659%

phrases related to concealed or hidden actions or attributes within a context

No Comments

No Known Activations