INDEX

Explanations

references to personal experiences or conditions related to individuals

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

suppress transcription

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

fromnode

-0.41

GOTREF

-0.37

XmlAccessType

-0.34

 correctes

-0.33

BindingSource

-0.32

 rentrer

-0.32

GeneratedMessage

-0.32

 nakalista

-0.31

 насељу

-0.30

Спољашње

-0.29

POSITIVE LOGITS

Fordítás

0.53

usermodel

0.52

الإنجليزية

0.50

 Italijanski

0.49

keyColumn

0.48

 виправивши

0.46

isamment

0.46

bolista

0.46

+")

0.46

quelize

0.45

Activations Density 0.063%

references to personal experiences or conditions related to individuals

suppress transcription

No Comments

No Known Activations