INDEX

Explanations

the beginning of a document

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

Code, numbers, and symbols

np_acts-logits-general · gemini-2.0-flash

legal citations and codes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ChildIndex

-0.55

westen

-0.51

 Billy

-0.48

 Hayden

-0.46

 stickers

-0.44

strokeWeight

-0.43

 kids

-0.43

iedler

-0.43

 sticker

-0.42

 Chinois

-0.42

POSITIVE LOGITS

EIF

0.91

RTEE

0.86

RTDA

0.84

RTHOOK

0.83

findpost

0.79

EIF

0.77

 Normdatei

0.74

Personensuche

0.73

évaluateur

0.72

 незавершена

0.71

Activations Density 0.001%

the beginning of a document

Code, numbers, and symbols

legal citations and codes

No Comments

No Known Activations