INDEX

Explanations

references to processes or actions being completed or confirmed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

face

-0.48

といけない

-0.44

ENDO

-0.43

baine

-0.43

und

-0.43

äls

-0.43

GetInt

-0.42

CE

-0.42

 zoals

-0.41

uró

-0.40

POSITIVE LOGITS

ագրություններ

0.99

ValueStyle

0.91

enumii

0.85

enumi

0.82

 arşivlendi

0.79

tvguidetime

0.79

 بيها

0.74

Dazu

0.72

Бахар

0.71

wikidata

0.71

Activations Density 0.485%

references to processes or actions being completed or confirmed

No Comments

No Known Activations