INDEX

Explanations

file paths or directory structures

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

file paths and programming terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 enfans

-0.73

 disambiguazione

-0.71

iſen

-0.66

majánló

-0.58

 ſche

-0.56

 ſes

-0.55

ésultats

-0.54

 TextInputType

-0.54

ðsíða

-0.54

 otomatig

-0.53

POSITIVE LOGITS

__(/*!

0.56

newArrayList

0.44

__*/

0.40

AddHtmlAttribute

0.39

getColumnIndex

0.38

]['

0.38

[*]

0.38

fjspx

0.37

centralwidget

0.36

listdir

0.36

Activations Density 0.041%

file paths or directory structures

file paths and programming terms

No Comments

No Known Activations