INDEX

Explanations

references to sports-related winning and scoring events

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

Prepositions and auxiliary verbs

np_acts-logits-general · gemini-2.0-flash

claim victory easily

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Datuak

-0.65

 Unmarshal

-0.56

 мәкал

-0.56

 AppColors

-0.52

יוחד

-0.51

 riuscito

-0.47

сунок

-0.46

 يتيمه

-0.46

didSet

-0.46

 tijde

-0.45

POSITIVE LOGITS

 easily

1.16

easily

1.06

 comfortably

1.04

 easy

1.04

Easy

0.97

 Easily

0.94

 Easy

0.91

easy

0.91

 rout

0.90

 romp

0.89

Activations Density 0.157%

references to sports-related winning and scoring events

Prepositions and auxiliary verbs

claim victory easily

No Comments

No Known Activations