INDEX

Explanations

references to individuals 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 amnesty

-0.65

bbero

-0.65

 Wayback

-0.60

 cenar

-0.59

 urbaine

-0.58

fördert

-0.57

 ratify

-0.57

 animados

-0.57

Hoping

-0.56

 Revenues

-0.56

POSITIVE LOGITS

 individual

3.30

Individual

3.08

 Individual

3.06

individual

3.04

 INDIVIDUAL

2.84

ividual

2.50

 individ

2.30

 individually

2.27

 Individ

2.24

Individ

2.20

Activations Density 0.050%

references to individuals or individual characteristics

No Comments

No Known Activations