INDEX

Explanations

programming-related terms and structure

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

Code related to layout weights or sizes

np_acts-logits-general · gemini-2.0-flash

indent, weight, size, idx

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

the

-0.49

 lenker

-0.48

www

-0.45

all

-0.42

con

-0.42

yr

-0.42

tuck

-0.42

www

-0.41

des

-0.41

{{\

-0.41

POSITIVE LOGITS

VersionUID

1.00

.*")]

0.94

 XNUMX

0.88

InSection

0.85

 defaultstate

0.82

+#+

0.82

ReusableCell

0.79

醐

0.79

awtextra

0.74

URLException

0.74

Activations Density 0.349%

programming-related terms and structure

Code related to layout weights or sizes

indent, weight, size, idx

No Comments

No Known Activations