INDEX

Explanations

terms and structures related to coding and software development

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

Code-related tokens, especially Java imports

np_acts-logits-general · gemini-2.0-flash

android imports and expressions

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

 lymp

-0.49

 uſed

-0.49

avoit

-0.48

 Wund

-0.48

 Lymp

-0.47

HtmlAttribute

-0.47

OGS

-0.47

 raiſ

-0.46



-0.46

зда

-0.45

POSITIVE LOGITS

0.60

saraba

0.59

 bArr

0.56

0.54

AndroidJUnit

0.53

wnątrz

0.53

 luas

0.53

 Quiet

0.52

verhält

0.51

お待ちしております

0.51

Activations Density 0.019%

terms and structures related to coding and software development

Code-related tokens, especially Java imports

android imports and expressions

No Comments

No Known Activations