INDEX

Explanations

proper names and titles of individuals

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

earchers

-0.78

ancies

-0.73

Topics

-0.73

minecraft

-0.73

itiveness

-0.71

xual

-0.70

dfx

-0.69

leans

-0.66

uates

-0.65

ologies

-0.62

POSITIVE LOGITS

Ã¡

0.78

ãĤ¼ãĤ¦ãĤ¹

0.78

vez

0.78

Ã¡n

0.74

USD

0.74

uria

0.72

Ã£o

0.72

«ĺ

0.71

 Borg

0.70

ãĥ¡

0.69

Activations Density 19.517%

proper names and titles of individuals

No Comments

No Known Activations