INDEX

Explanations

keywords related to programming libraries or frameworks

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

-0.53

man

-0.52

 rise

-0.52

-0.50

漠

-0.49

 include

-0.48

Man

-0.48

</td>

-0.48

POSITIVE LOGITS

ſelves

0.85

 colouring

0.80

RectangleBorder

0.80

 houſe

0.79

 neceff

0.77

 Савезне

0.76

 muualla

0.76

UserScript

0.75

 faſt

0.75

 ſche

0.74

Activations Density 0.078%

keywords related to programming libraries or frameworks

No Comments

No Known Activations