INDEX

Explanations

snippets of code or style definitions in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 InputDecoration

-0.72

 سكانية

-0.55

 relâche

-0.55

 veda

-0.54

ạp

-0.53

 loob

-0.52

]--;

-0.52

Enllaços

-0.52

Šaltiniai

-0.51

 pessi

-0.50

POSITIVE LOGITS

={{

0.81

mstyle

0.70

RectangleBorder

0.66

 TextAppearance

0.64

<h6>

0.62

semantics

0.60

原始内容存档于

0.59

richTextPanel

0.57

 CreateTagHelper

0.56

 ammat

0.55

Activations Density 0.013%

snippets of code or style definitions in a document

No Comments

No Known Activations