INDEX

Explanations

expressions related to personal beliefs or statements

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

Follows an apostrophe

np_acts-logits-general · gemini-2.0-flash

political and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

contentLoaded

-0.68

 Meksiku

-0.58

...');

-0.55

medriver

-0.55

 Paglinawan

-0.54

setVerticalGroup

-0.54

醐

-0.54

 SqlParameter

-0.53

anty

-0.53

Ответить

-0.52

POSITIVE LOGITS

CrossRef

0.57

réhen

0.56

ósitos

0.52

 JSONException

0.48

 plă

0.47

 fhall

0.46

bindValue

0.46

 tuong

0.45

 Lucre

0.45

hoeddwyd

0.44

Activations Density 0.075%

expressions related to personal beliefs or statements

Follows an apostrophe

political and technical terms

No Comments

No Known Activations