INDEX

Explanations

code structure and function definitions

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

Numbers inside parentheses or brackets

np_acts-logits-general · gemini-2.0-flash

code syntax endings

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

 crystal

-0.54

 chio

-0.53

mybatisplus

-0.51

STRENGTH

-0.51

spouse

-0.51

ราช

-0.50

 Crystal

-0.49

 Brief

-0.49

crystal

-0.49

문

-0.49

POSITIVE LOGITS

tagHelperRunner

0.71

 nahilalakip

0.69

 CreateTagHelper

0.68

 HasFactory

0.65

 pinulongan

0.58

TAWA

0.58

UserScript

0.56

findpost

0.55

tening

0.55

providedIn

0.53

Activations Density 0.210%

code structure and function definitions

Numbers inside parentheses or brackets

code syntax endings

No Comments

No Known Activations