INDEX

Explanations

phrases and references related to something being in or associated with the "back" of an object or location

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

front and back locations

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

Not in Any Lists

No Comments

Negative Logits

 zatem

-0.46

 către

-0.46

 singkat

-0.43

 voorbij

-0.42

 دریافت‌شده

-0.40

 lecz

-0.40

 koszulka

-0.40

 tunggal

-0.40

hingga

-0.39

 feira

-0.38

POSITIVE LOGITS

 Front

0.63

 rear

0.61

Front

0.59

 Rear

0.57

 front

0.57

Rear

0.56

Middle

0.55

rear

0.55

 FRONT

0.53

 intptr

0.53

Activations Density 0.010%

phrases and references related to something being in or associated with the "back" of an object or location

front and back locations

No Comments

No Known Activations

phrases and references related to something being in or associated with the "back" of an object or location

front and back locations

No Comments

No Known Activations