INDEX

Explanations

repeated phrases or structures in text

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

and, but,

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

 arşivlendi

-0.48

 XNUMX

-0.47

UserScript

-0.47

 HasFactory

-0.46

initializeApp

-0.46

Kaynakça

-0.46

 calldata

-0.46

 pele

-0.44

みてください

-0.43

currentColor

-0.42

POSITIVE LOGITS

!,

0.57

0.54

RegressionTest

0.50

,...

0.49

 '=',

0.48

.,

0.48

saraba

0.48

 चल

0.47

,-,

0.47

########.

0.47

Activations Density 0.020%

repeated phrases or structures in text

and, but,

No Comments

No Known Activations