INDEX

Explanations

punctuation marks and formatting symbols in text

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

start of turn, user

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

JsonFormat

-0.55

Portail

-0.50

ᅠ

-0.49

abestanden

-0.49

ngdoc

-0.48

PickerController

-0.46

UrlResolution

-0.45

gwt

-0.44

InSection

-0.44

ఞ

-0.43

POSITIVE LOGITS

UTERS

0.56

rawDesc

0.50

 intptr

0.48

Hentet

0.47

 nakalista

0.46

ScopeManager

0.41

 AssemblyProduct

0.41

 censiti

0.40

findpost

0.40

OCCURRED

0.39

Activations Density 0.000%

punctuation marks and formatting symbols in text

start of turn, user

No Comments

No Known Activations