INDEX

Explanations

patterns indicating complex data structures or programming elements

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

lo

-0.57

 fully

-0.56

chik

-0.55

спо

-0.52

ern

-0.50

御

-0.50

<0xE8>

-0.49

to

-0.48

di

-0.48

comp

-0.48

POSITIVE LOGITS

 Мексичка

1.13

 Baillargeon

0.92

BibitemShut

0.88

StoryboardSegue

0.85

 تانيه

0.85

bibfield

0.84

Efq

0.83

GraphicsUnit

0.83

 myſelf

0.83

Filmografie

0.80

Activations Density 0.491%

patterns indicating complex data structures or programming elements

No Comments

No Known Activations