INDEX

Explanations

phrases related to social or political issues

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

bia

-0.76

hap

-0.70

 Ruin

-0.67

ofi

-0.66

 Ramp

-0.65

itars

-0.65

 Glac

-0.64

overty

-0.63

olulu

-0.62

 Parenthood

-0.61

POSITIVE LOGITS

soType

0.80

ature

0.80

Hug

0.68

 conclud

0.66

table

0.65

Table

0.64

 analytical

0.63

rences

0.63

 analys

0.63

isSpecialOrderable

0.63

Activations Density 7.623%

phrases related to social or political issues

No Comments

No Known Activations