INDEX

Explanations

expressions of similarity and comparison

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

sameness and similarity comparisons

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

AnchorStyles

-0.46

 متحده

-0.45

دانشنامهٔ

-0.43

 betweenstory

-0.43

 jScrollPane

-0.41

 SQLAlchemy

-0.41

 AspNetCore

-0.41

 psychoanalysis

-0.40

ViewChild

-0.40

 مواليد

-0.40

POSITIVE LOGITS

同样的

0.49

RenderAtEndOf

0.49

同樣

0.49

 similar

0.48

complexContent

0.45

 similarly

0.44

同様

0.44

 same

0.42

similar

0.41

 pareil

0.41

Activations Density 0.040%

expressions of similarity and comparison

sameness and similarity comparisons

No Comments

No Known Activations