INDEX

Explanations

references to extras in media content, especially related to interviews and special features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

LabelTagHelper

-0.56

RuleContext

-0.50



-0.49

 kasarigan

-0.44

cui

-0.44

THING

-0.44

COLOG

-0.43

gpl

-0.43

****************

-0.43

qai

-0.42

POSITIVE LOGITS

 تضيفلها

0.68

脚注の使い方

0.64

Efq

0.63

 NSCoder

0.63

 himſelf

0.61

 Mémoires

0.60

 myſelf

0.58

 createStore

0.57

 tslint

0.57

 chofe

0.56

Activations Density 0.886%

references to extras in media content, especially related to interviews and special features

No Comments

No Known Activations