INDEX

Explanations

keywords related to measurements and classifications

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

lists of technical or descriptive terms

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

didSet

-0.53

 iſt

-0.50

 Roskov

-0.48

FunctionFlags

-0.47

 ErrIntOverflow

-0.46

 AssemblyCulture

-0.45

RTLR

-0.42

StoryboardSegue

-0.42

 seyn

-0.40

MessageTagHelper

-0.40

POSITIVE LOGITS

참고

0.48

ագրություններ

0.41

parsedMessage

0.40

 đón

0.40

絡

0.39

 Photocase

0.37

NOPQRST

0.36

hadap

0.36

hoeddwyd

0.36

amitié

0.35

Activations Density 0.106%

keywords related to measurements and classifications

lists of technical or descriptive terms

No Comments

No Known Activations