INDEX

Explanations

specialized technical or code-related information

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

Code snippets and file paths

np_acts-logits-general · gemini-2.0-flash

specific studies or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

burgh

-0.47

 épais

-0.45

 massive

-0.44

-0.43

CreateModel

-0.43

NewReader

-0.43

 frattempo

-0.43

 grasa

-0.43

new

-0.43

POSITIVE LOGITS

celotti

0.71

DockStyle

0.68

>{@

0.66

Viitteet

0.65

GIH

0.63

">//

0.62

WireFormat

0.61

 ISNI

0.60

GEBURTSDATUM

0.60

ïsme

0.59

Activations Density 0.012%

specialized technical or code-related information

Code snippets and file paths

specific studies or comparisons

No Comments

No Known Activations