INDEX

Explanations

expressions of cognition or belief in relation to specific ideas or concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

knowing that

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Infórmanos

-0.69

 ModelExpression

-0.63

⁛

-0.54

esModule

-0.53

bbean

-0.52

卺

-0.49

Portail

-0.49

ôtel

-0.48

OrWhiteSpace

-0.48

concer

-0.48

POSITIVE LOGITS

 knowing

0.46

 assuming

0.40

tanleria

0.40

 Administrativna

0.38

Архівовано

0.34

 informée

0.33

 perquè

0.33

 Knowing

0.33

 Assuming

0.33

 ohne

0.33

Activations Density 0.050%

expressions of cognition or belief in relation to specific ideas or concepts

knowing that

No Known Activations