INDEX

Explanations

references to notable persons, places, or events

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

names and events

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

argout

-0.41

writeFieldEnd

-0.40

ApiModelProperty

-0.38

NamedQueries

-0.38

ResponseWriter

-0.37

fillable

-0.36

⏟

-0.35

 callbacks

-0.35

bolistas

-0.35

PyExc

-0.35

POSITIVE LOGITS

SourceChecksum

0.56

ViewImports

0.48

 ब्रेकडाउन

0.47

 juſ

0.44

UserScript

0.44

 noDo

0.43

 препратки

0.42

OGND

0.42

ひとつ

0.42

afficheront

0.41

Activations Density 0.674%

references to notable persons, places, or events

names and events

No Comments

No Known Activations