INDEX

Explanations

names of individuals, particularly individuals related to media or politics

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

ĸļ

-0.49

ngth

-0.45

SOURCE

-0.42

ogo

-0.40

 Remastered

-0.38

Iv

-0.37

iors

-0.36

 Santos

-0.35

Category

-0.35

itivity

-0.34

POSITIVE LOGITS

iston

0.36

hovah

0.36

 Against

0.35

ocalypse

0.35

fill

0.35

 hotline

0.33

 Ticket

0.33

tery

0.33

 ticket

0.33

swick

0.32

Activations Density 0.213%

names of individuals, particularly individuals related to media or politics

No Comments

No Known Activations