INDEX

Explanations

references to specific terms or concepts denoted by the letter 'r'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ed

-0.66

WEBPACK

-0.55

ことが

-0.48

ent

-0.48

ew

-0.48

acij

-0.46

é

-0.46

 ***!

-0.46

ate

-0.45

POSITIVE LOGITS

 resourceCulture

0.70

IUrlHelper

0.70

IsMutable

0.69

 CreateTagHelper

0.64

 Nautilus

0.62

 JpaRepository

0.59

ⓧ

0.59

 carottes

0.58

tvguidetime

0.58

 Stardust

0.57

Activations Density 0.221%

references to specific terms or concepts denoted by the letter 'r'

No Comments

No Known Activations