INDEX

Explanations

phrases indicating divisions or components of a whole

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

PostExecute

-0.64

/\.

-0.61

TintMode

-0.59

 Reverso

-0.59

usermodel

-0.56

 ddelweddau

-0.56

 копия

-0.55

ByVersion

-0.55

 <>",

-0.54

ancies

-0.54

POSITIVE LOGITS

 integrante

0.74

 part

0.72

 integral

0.58

integral

0.56

 integrated

0.54

 súčas

0.54

integrated

0.53

 onderdeel

0.52

 bagian

0.50

($__

0.49

Activations Density 0.083%

phrases indicating divisions or components of a whole

No Comments

No Known Activations