INDEX

Explanations

references to organizations, institutions, or funding sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 itſelf

-0.99

 myſelf

-0.91

ſelves

-0.91

 CHAPITRE

-0.90

bibfield

-0.85

 themſelves

-0.85

 ویکی‌پدیای

-0.84

ſelf

-0.83

 Theſe

-0.82

 raiſ

-0.82

POSITIVE LOGITS

plus

0.68

+.

0.63

0.58

+,

0.56

label

0.55

AV

0.54

AV

0.52

 Plus

0.52

–

0.49

Activations Density 0.233%

references to organizations, institutions, or funding sources

No Comments

No Known Activations