INDEX

Explanations

moments of emotional significance and impactful statements

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

documentation and code comments

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

 resourceCulture

-0.57

 beginnetje

-0.55

 ſte

-0.52

Erreferentziak

-0.50

ſelves

-0.50

CrossRef

-0.49

Aholisi

-0.49

Jîn

-0.49

ſelf

-0.48

Παραπομπές

-0.48

POSITIVE LOGITS

.*")]

0.57

 Walkover

0.52

Reprodução

0.51

ագրություններ

0.50

Gur

0.50

Gur

0.48

Dok

0.47

 Vendor

0.47

 Վերցված

0.47

zzare

0.47

Activations Density 0.081%

moments of emotional significance and impactful statements

documentation and code comments

No Comments

No Known Activations