INDEX

Explanations

occurrences of headers or markers denoting new sections or segments in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

IVEREF

-0.78

最快更新

-0.70

 utafitiHapana

-0.70

EndGlobalSection

-0.69

shadowOpacity

-0.69

 himo

-0.69

ImageContext

-0.68

numerusform

-0.68

хьтан

-0.66

EDEFAULT

-0.65

POSITIVE LOGITS

ry

0.71

me

0.66

ValueStyle

0.54

ia

0.53

ri

0.48

Else

0.45

ut

0.45

RI

0.42

PRWEB

0.42

bilang

0.42

Activations Density 1.646%

occurrences of headers or markers denoting new sections or segments in the text

No Comments

No Known Activations