INDEX

Explanations

references to buffer management in programming contexts

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

data buffer operations

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

AndEndTag

-0.63

 surla

-0.61

UserScript

-0.58

basicConfig

-0.57

iC

-0.55

//

-0.54

"%"

-0.54

AddAttribute

-0.54

mmmm

-0.53

AddWithValue

-0.53

POSITIVE LOGITS

buf

1.01

buf

0.98

Buf

0.92

Buf

0.79

ByteBuf

0.78

BUF

0.77

BUF

0.75

bufio

0.68

uf

0.57

setMsg

0.56

Activations Density 0.006%

references to buffer management in programming contexts

data buffer operations

No Comments

No Known Activations