INDEX

Explanations

mentions of specific rules and guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

tvguidetime

-0.85

`,

-0.69

]),

-0.66

håll

-0.64

 isInitialized

-0.61

'])){

-0.61

>",

-0.61

ViewInit

-0.59

 appunto

-0.59

RequiresApi

-0.59

POSITIVE LOGITS

 closet

0.75

 Opportunities

0.73

Opportunities

0.73

はじめに

0.64

 opportunities

0.64

opportunities

0.62

Opp

0.62

 Closet

0.61

 dialed

0.60

moveToFirst

0.59

Activations Density 0.105%

mentions of specific rules and guidelines

No Comments

No Known Activations