INDEX

Explanations

code structure and formatting elements

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

foreign language descriptions

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

cloudflare

-0.34

 bénévoles

-0.33

 strcmp

-0.33

 entgegen

-0.32

Sortie

-0.32

 serem

-0.31

insertion

-0.31

 actionPerformed

-0.31

saraba

-0.30

 énergé

-0.30

POSITIVE LOGITS

KURZBESCHREIBUNG

0.73

expandindo

0.69

 '\\;'

0.66

RegressionTest

0.65

AutoScaleMode

0.65

 ویکی‌پدی

0.61

AddTagHelper

0.60

 ModelExpression

0.59

المكان

0.58

 препратки

0.56

Activations Density 0.003%

code structure and formatting elements

foreign language descriptions

No Comments

No Known Activations