INDEX

Explanations

concepts related to learned associations and their implications in collective understanding

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

associated meanings and connotations

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

 ब्रेकडाउन

-0.47

mybatisplus

-0.43

addContainerGap

-0.41

Pratique

-0.41

calça

-0.40

BibitemShut

-0.39

moteur

-0.36

 GenerationType

-0.35

 BoxFit

-0.35

照

-0.35

POSITIVE LOGITS

 connotations

0.52

 prejudices

0.50

 familiarity

0.49

 ujednoznacz

0.48

 perceptions

0.48

sizeCache

0.47

 notions

0.47

 precon

0.46

windowFixed

0.45

 Autorisations

0.45

Activations Density 0.035%

concepts related to learned associations and their implications in collective understanding

associated meanings and connotations

No Comments

No Known Activations