INDEX

Explanations

references to figures and tables in scientific documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 AssemblyCulture

-0.85

and

-0.51

 Wicidata

-0.49

AndEndTag

-0.46

 yourself

-0.45

 neither

-0.45

LIO

-0.44

jstor

-0.44

No

-0.44

⏟

-0.44

POSITIVE LOGITS

tvguidetime

0.65

 חיצוניים

0.63

Nip

0.57

 ſtate

0.57

 Silas

0.57

 enlargement

0.57

 Majefty

0.56

typeorm

0.56

 Houſe

0.56

 Coliseum

0.55

Activations Density 0.574%

references to figures and tables in scientific documents

No Comments

No Known Activations