INDEX

Explanations

references to authors and their affiliations

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

author attributions and names

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

 Италијани

-0.59

 bileklik

-0.52

AnchorStyles

-0.52

 '\\;'

-0.50

 sostenible

-0.50

 adopción

-0.49

 Infór

-0.49

 manguera

-0.48

 régulière

-0.48

 mikina

-0.48

POSITIVE LOGITS

ParallelGroup

0.50

Mol

0.49

 Market

0.47

 Team

0.47

 team

0.46

 Fisher

0.46

Mul

0.46

 Thermal

0.46

Vo

0.45

 Vign

0.45

Activations Density 0.012%

references to authors and their affiliations

author attributions and names

No Comments

No Known Activations