INDEX

Explanations

header tags indicating sections and structure 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 @ 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

SharedDtor

-0.73

Amicalement

-0.71

Erfolge

-0.69

LookAnd

-0.68

 الرياضيه

-0.68

UnsafeEnabled

-0.67

 تضيفلها

-0.66

bootstrapcdn

-0.66

RefNanny

-0.66

 AssemblyCulture

-0.65

POSITIVE LOGITS

<strong>

1.06

<b>

0.83

What

0.83

<h2>

0.80

<em>

0.78

The

0.75

“

0.74

 chré

0.71

 RELATED

0.69

Activations Density 0.010%

header tags indicating sections and structure in a document

No Comments

No Known Activations