INDEX

Explanations

the beginning of the document and introductory phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Jereo

-0.55

 Giuli

-0.48

isticas

-0.47

̀i

-0.45

Personendaten

-0.45

 Hygge

-0.44

 Flatten

-0.44

 Gaia

-0.44

✭✭

-0.43

 shared

-0.43

POSITIVE LOGITS

!*\

0.60

 resourceCulture

0.57

tvguidetime

0.57

 muualla

0.56

хьтан

0.54

rungsseite

0.53

 Waray

0.53

CWE

0.53

 متحده

0.53

脚注の使い方

0.53

Activations Density 0.005%

the beginning of the document and introductory phrases

No Comments

No Known Activations