INDEX

Explanations

punctuation marks, specifically periods

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

 múl

-0.40

utilities

-0.39

hooks

-0.37

AddArg

-0.37

 JpaRepository

-0.37

 shutil

-0.36

jsonPath

-0.36

 trekken

-0.36

occasione

-0.36

 détail

-0.36

POSITIVE LOGITS

Personendaten

0.96

initState

0.69

 &___

0.66

 useState

0.66

omitempty

0.59

 Administrativna

0.57

 StatefulWidget

0.56

Jereo

0.56

nonatomic

0.54

UnusedPrivate

0.54

Activations Density 0.001%

punctuation marks, specifically periods

<start_of_turn> user

No Comments

No Known Activations

punctuation marks, specifically periods

<start_of_turn> user

No Comments

No Known Activations