INDEX

Explanations

references to bugs and error conditions in software documentation

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

URL , code , bug

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 kaynağından

-0.34

よう

-0.32

 оригіналу

-0.31

ṃ

-0.29

isNameExpr

-0.28

istoitu

-0.27

 jing

-0.26

有个

-0.25

addCriterion

-0.25

 capital

-0.25

POSITIVE LOGITS

rawDesc

0.66

MarshalTo

0.61

 GenerationType

0.60

 nakalista

0.58

XmlAccessType

0.58

 riuscito

0.57

 disambiguazione

0.57

enderror

0.57

 paixão

0.56

awtextra

0.56

Activations Density 0.329%

references to bugs and error conditions in software documentation

URL , code , bug

No Comments

No Known Activations