INDEX

Explanations

keywords related to data structures and programming concepts

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

Non-English words or code

np_acts-logits-general · gemini-2.0-flash

code identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Topf

-0.55

Kritik

-0.51

 <>",

-0.50

 Empieza

-0.50

 complained

-0.48

URATION

-0.46

 Decke

-0.46

 varm

-0.46

 Bergmann

-0.46

semana

-0.45

POSITIVE LOGITS

ngrx

0.43

 ويكيپيديا

0.40

LikeLike

0.40

 pinulongan

0.38

RTHOOK

0.38

.}~\

0.37

abestanden

0.37

Kapcsolódó

0.37

inkscape

0.36

Autoritní

0.35

Activations Density 1.637%

keywords related to data structures and programming concepts

Non-English words or code

code identifiers

No Comments

No Known Activations