INDEX

Explanations

instances of the word "hat" in various forms and contexts

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

mathematical hat notation

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

 Primo

-0.57

MBC

-0.56

CBC

-0.53

 Claudio

-0.50

()));

-0.49

CEE

-0.49

 Clair

-0.48

 Rockville

-0.48

miro

-0.48

DCE

-0.48

POSITIVE LOGITS

Hat

1.07

Hat

1.01

hat

0.97

hat

0.93

 hats

0.85

HAT

0.84

HAT

0.82

Hats

0.79

 Hats

0.78

 Hatfield

0.77

Activations Density 0.038%

instances of the word "hat" in various forms and contexts

mathematical hat notation

No Comments

No Known Activations