INDEX

Explanations

instances of the word "by" associated with attribution or authorship in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ThroughAttribute

-0.88

ScopeManager

-0.79

Хьажоргаш

-0.75

 Winaray

-0.72

kloped

-0.71

 protoimpl

-0.70

<_>

-0.70

انجليز

-0.69

SourceChecksum

-0.68

 ModelExpression

-0.68

POSITIVE LOGITS

by

0.96

by

0.82

ByName

0.70

By

0.65

By

0.64

ByEmail

0.59

 oleh

0.55

ByKey

0.54

 Vía

0.52

getBy

0.51

Activations Density 0.139%

instances of the word "by" associated with attribution or authorship in text

No Comments

No Known Activations