INDEX

Explanations

references to method calls related to size and dimensions

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

ewel

-0.47

hwar

-0.45

Esa

-0.44

 thần

-0.44

 كومونز

-0.43

 ditangkap

-0.42

ianto

-0.41

Above

-0.40

 Commission

-0.39

']>

-0.39

POSITIVE LOGITS

出版年

0.90

setupUi

0.77

GEBURTSDATUM

0.73

MigrationBuilder

0.72

 ModelExpression

0.65

 pinulongan

0.64

 ReSharper

0.61

_$

0.60

invokeLater

0.59

 Exactos

0.59

Activations Density 0.137%

references to method calls related to size and dimensions

No Comments

No Known Activations