INDEX

Explanations

programmatic structures and syntax used in code

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

Code accessing array elements

np_acts-logits-general · gemini-2.0-flash

extracting declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UserScript

-0.67

Tembelea

-0.63

Билгалдахарш

-0.61

 كومونز

-0.60

 <=",

-0.58

]")]

-0.58

 "..\..\

-0.58

KommentareTeilen

-0.56

expandindo

-0.56

ⓘ

-0.56

POSITIVE LOGITS

 first

0.78

'][

0.73

()[

0.72

[-

0.72

0.71

first

0.71

')[

0.69

")[

0.69

 objectAtIndex

0.66

"][

0.65

Activations Density 0.124%

programmatic structures and syntax used in code

Code accessing array elements

extracting declarations

No Comments

No Known Activations