INDEX

Explanations

references to media outlets and publications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-0.73

houding

-0.51

SharedCtor

-0.50

jsdelivr

-0.49

 xuyên

-0.48

atiker

-0.47

 OMITBAD

-0.47

unteers

-0.46

npmjs

-0.45

 Cytometry

-0.45

POSITIVE LOGITS

 Daily

0.87

 News

0.87

News

0.86

news

0.85

Daily

0.83

 news

0.83

 magazine

0.80

 Magazine

0.80

onews

0.79

Tribune

0.78

Activations Density 0.254%

references to media outlets and publications

No Comments

No Known Activations