INDEX

Explanations

categories and classifications of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

webElementXpaths

-0.80

Personensuche

-0.79

uxxxx

-0.77

حياتها

-0.72

Демографія

-0.70

RLock

-0.69

sizeCache

-0.67

ตร์

-0.67

RenderAtEndOf

-0.66

utuhkan

-0.66

POSITIVE LOGITS

 getCategory

1.11

 category

1.08

 categories

1.01

 CATEGORY

0.97

 Category

0.96

Category

0.89

 Categories

0.86

categories

0.84

getCategory

0.84

 categorize

0.82

Activations Density 0.154%

categories and classifications of content

No Comments

No Known Activations