INDEX

Explanations

attributes and specifications related to items or objects

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

dimensions and counts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MLLoader

-0.70

parsedMessage

-0.66

ագրություններ

-0.65

tagHelperRunner

-0.63

 चीज़ों

-0.60

IsContent

-0.59

 мәкал

-0.58

 Италијани

-0.58

SequentialGroup

-0.56

UrlResolution

-0.56

POSITIVE LOGITS

 size

0.51

size

0.42

 range

0.39

 sizes

0.38

 sized

0.38

 Size

0.36

 minimum

0.36

 Luxury

0.35

 thickness

0.35

 المعد

0.35

Activations Density 0.012%

attributes and specifications related to items or objects

dimensions and counts

No Comments

No Known Activations