INDEX

Explanations

proper nouns and references to specific entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

RegressionTest

-0.72

verwijspagina

-0.61

 وتسجيلات

-0.59

 صوتيه

-0.59

uxxxx

-0.57

richTextPanel

-0.55

ViewImports

-0.52

 simplifié

-0.50

InjectAttribute

-0.50

principalColumn

-0.50

POSITIVE LOGITS

WWE

1.09

WWE

0.94

wwe

0.74

wwe

0.66

 wrestling

0.52

 Wrestling

0.52

 wrestler

0.45

 poffe

0.45

restling

0.43

 Reſ

0.43

Activations Density 0.000%

proper nouns and references to specific entities or organizations

No Comments

No Known Activations