INDEX

Explanations

references to individual experiences or individual characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Wayback

-0.67

 amnesty

-0.59

">//

-0.55

 cenar

-0.54

bbero

-0.52

ampa

-0.52

 Hailey

-0.52

рг

-0.52

cleros

-0.51

reportError

-0.51

POSITIVE LOGITS

 individual

3.72

Individual

3.56

 Individual

3.51

individual

3.49

 INDIVIDUAL

3.21

ividual

2.68

 individually

2.62

 individ

2.58

 Individ

2.58

individ

2.53

Activations Density 0.069%

references to individual experiences or individual characteristics

No Comments

No Known Activations