INDEX

Explanations

phrases indicating conditionality or specificity in claims and statements

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

Chham

-0.59

 Comprometido

-0.41

bebasan

-0.35

arriver

-0.35

ädchen

-0.34

 PLWABN

-0.32

पया

-0.32

セラー

-0.29

 trône

-0.28

 angekommen

-0.28

POSITIVE LOGITS

:✨

1.44

[*]

0.73

fromnode

0.68

 betweenstory

0.64

IntoConstraints

0.62

UnsafeEnabled

0.59

Tal

0.56

💼

0.54

reportWebVitals

0.51

 pinulongan

0.51

Activations Density 0.192%

phrases indicating conditionality or specificity in claims and statements

No Comments

No Known Activations