INDEX

Explanations

references to icons or icon-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

↵↵

-0.49

 onderstaande

-0.48

da

-0.48

the

-0.48

DispatchToProps

-0.46

In

-0.46

‘

-0.44

stå

-0.43

de

-0.43

POSITIVE LOGITS

AndEndTag

1.04

 Token

1.03

 otomatig

0.86

 token

0.84

OGND

0.82

 poffe

0.81

findpost

0.81

 TOKEN

0.80

 تانيه

0.79

ViewImports

0.78

Activations Density 0.135%

references to icons or icon-related elements

No Comments

No Known Activations