INDEX

Explanations

interactive elements or actions related to images and links 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

oredCriteria

-0.78

 незавершена

-0.76

脚注の使い方

-0.69

 dAtA

-0.68

 CreateTagHelper

-0.67

expandindo

-0.67

mergeFrom

-0.67

PerformLayout

-0.66

 TestBed

-0.66

FormTagHelper

-0.63

POSITIVE LOGITS

Попис

0.51

UpInside

0.51

 click

0.47

Intent

0.45

 onItemClick

0.45

 tickets

0.44

 details

0.44

فحة

0.42

леге

0.41

 exploration

0.41

Activations Density 0.316%

interactive elements or actions related to images and links in a document

No Comments

No Known Activations