INDEX

Explanations

political and news-related terms, especially related to Democratic presidential candidates and political events

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

rawdownloadcloneembedreportprint

-0.37

 fres

-0.35

 inver

-0.34

rys

-0.33

izo

-0.33

ayne

-0.32

izons

-0.32

ĸļ

-0.32

ilion

-0.32

avorite

-0.32

POSITIVE LOGITS

 Clintons

0.32

 Gets

0.32

'[

0.32

 Countdown

0.31

?'"

0.31

 Beware

0.31

 Doesn

0.31

poses

0.30

 Bucket

0.30

Activations Density 8.737%

political and news-related terms, especially related to Democratic presidential candidates and political events

No Comments

No Known Activations