INDEX

Explanations

references to books and related terms

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

The literal word "Book"

np_acts-logits-general · gemini-2.0-flash

book followed by activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

⁡

-0.63

]--;

-0.56

UTERS

-0.55

GID

-0.54

setAccessible

-0.54

)),

-0.53

)";

-0.52

siapkan

-0.52

postmedia

-0.52

VersionUID

-0.51

POSITIVE LOGITS

books

0.93

 books

0.92

helves

0.88

ends

0.79

Books

0.78

 Books

0.78

helf

0.76

worm

0.74

Bok

0.68

ended

0.67

Activations Density 0.082%

references to books and related terms

The literal word "Book"

book followed by activity

No Comments

No Known Activations