INDEX

Explanations

references to academic journals and their associated metrics or publications

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

academic publications

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

SourceChecksum

-0.64

RTEX

-0.59

 InputMaybe

-0.57

__(/*!

-0.57

 OMITBAD

-0.54

Diweddarwch

-0.54

INCREF

-0.53

הערות

-0.50

 Geiſt

-0.50

parsedMessage

-0.50

POSITIVE LOGITS

 published

0.43

 Magazine

0.41

 publication

0.36

astify

0.36

 publications

0.35

publication

0.34

 magazine

0.34

®

0.34

 Series

0.34

 septembrie

0.33

Activations Density 0.117%

references to academic journals and their associated metrics or publications

academic publications

No Comments

No Known Activations