INDEX

Explanations

references to popular culture and entertainment franchises

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

it has

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

centralwidget

-0.39

 dance

-0.37

pam

-0.35

 repeat

-0.34

 protected

-0.34

 đau

-0.33

dance

-0.33

svc

-0.32

 consciência

-0.32

 safe

-0.31

POSITIVE LOGITS

adaptiveStyles

0.63

 LEGO

0.59

 Minif

0.56

CloseOperation

0.53

oa̍t

0.51

LEGO

0.50

jago

0.50

InjectAttribute

0.49

 tende

0.49

RTEE

0.49

Activations Density 0.005%

references to popular culture and entertainment franchises

it has

No Comments

No Known Activations