INDEX

Explanations

commands and functions related to manipulating data structures in programming

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

insertion and appending

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 насељу

-0.56

MessageOf

-0.54

OGND

-0.51

asteroide

-0.49

 queſta

-0.47

WriteBarrier

-0.47

 zoude

-0.46

ToProps

-0.45

 couver

-0.45

ToBounds

-0.45

POSITIVE LOGITS

insertBefore

0.49

 addition

0.48

mid

0.47

 inserted

0.44

insert

0.44

addGap

0.41

 insertion

0.41

 insert

0.41

 placement

0.39

 inserting

0.39

Activations Density 0.023%

commands and functions related to manipulating data structures in programming

insertion and appending

No Comments

No Known Activations