INDEX

Explanations

terms related to individuality and personal characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

cleros

-0.74

ç

-0.65

 Hélène

-0.62

 Koning

-0.62

CLO

-0.61

Fon

-0.60

 Hailey

-0.59

CLO

-0.59

resh

-0.59

 karş

-0.59

POSITIVE LOGITS

 individual

2.17

 Individual

2.17

 INDIVIDUAL

2.15

Individual

2.13

individual

2.04

ividual

1.89

Individuals

1.85

 Individuals

1.80

 individuals

1.79

IVIDUAL

1.76

Activations Density 0.066%

terms related to individuality and personal characteristics

No Comments

No Known Activations