INDEX

Explanations

references to characters and their relationships in a narrative context

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

coloured with Copic pens

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

 Audiodateien

-0.62

nloa

-0.56

脚注の使い方

-0.56

 poveznice

-0.49

webElementXpaths

-0.48

 الحره

-0.45

 الرياضيه

-0.44

 particulières

-0.43

WriteTagHelper

-0.42

 ModelExpression

-0.42

POSITIVE LOGITS

isContained

0.43

iverr

0.41

 vore

0.40

jsxFileName

0.40

aarrggbb

0.39

swing

0.38

 ProtoMessage

0.37

complexType

0.36

 Westfield

0.36

 Eldridge

0.35

Activations Density 0.024%

references to characters and their relationships in a narrative context

coloured with Copic pens

No Comments

No Known Activations