INDEX

Explanations

references to reviews and critical assessments of films

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

critical reviews

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

ьаж

-0.56

 Infórmanos

-0.55

CloseOperation

-0.55

 houſe

-0.55

 juſ

-0.51

EndContext

-0.49

queryInterface

-0.48

usermodel

-0.48

TagMode

-0.48

MVH

-0.47

POSITIVE LOGITS

 critic

0.53

critic

0.47

 reviewer

0.45

 wrote

0.44

 Escribe

0.42

 crítico

0.41

 Critic

0.41

 crítica

0.41

 critics

0.41

 review

0.40

Activations Density 0.035%

references to reviews and critical assessments of films

critical reviews

No Comments

No Known Activations