INDEX

Explanations

references to conflict and danger in narratives

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

ally vs enemy distinction

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

complexContent

-0.50

ArrowToggle

-0.49

__(/*!

-0.49

oforte

-0.49

oa̍t

-0.48

InjectAttribute

-0.46

compensation

-0.45

oredCriteria

-0.45

AVR

-0.44

addCriterion

-0.44

POSITIVE LOGITS

mut

0.45

 cherchés

0.43

enderror

0.41

lems

0.41

yntaxException

0.40

wag

0.40

 friendly

0.37

PullParser

0.37

 arşivlendi

0.36

tolua

0.36

Activations Density 0.102%

references to conflict and danger in narratives

ally vs enemy distinction

No Comments

No Known Activations