INDEX

Explanations

instances of the word "start" and variations related to beginnings or initial processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CrossRef

-1.03

évaluateur

-0.81

 scolas

-0.80

 jSON

-0.77

queryInterface

-0.77

 judiciaire

-0.71

 newArray

-0.71

///</

-0.70

 Cayman

-0.69

ThemeOverlay

-0.69

POSITIVE LOGITS

Start

1.61

 Start

1.59

start

1.55

START

1.54

 START

1.44

 start

1.39

getStart

1.27

 getStart

1.06

 Begin

1.04

estart

1.01

Activations Density 0.060%

instances of the word "start" and variations related to beginnings or initial processes

No Comments

No Known Activations