INDEX

Explanations

tokens related to programming syntax and function calls

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

Code snippets with parentheses and brackets

np_acts-logits-general · gemini-2.0-flash

function/method call 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

 snippetHide

-0.82

 Roskov

-0.68

 useAppContext

-0.64

ResumeLayout

-0.62

ConverterFactory

-0.61

 defaultstate

-0.61

UIControlState

-0.60

medriver

-0.60

 useRef

-0.59

 noDo

-0.58

POSITIVE LOGITS

ագրություններ

0.62

Pfalz

0.60

 betweenstory

0.56

levance

0.56

ыгана

0.53

таратура

0.51

 correctes

0.47

ategy

0.46

kmal

0.45

pensive

0.45

Activations Density 0.096%

tokens related to programming syntax and function calls

Code snippets with parentheses and brackets

function/method call endings

No Comments

No Known Activations