INDEX

Explanations

mentions of groups and classifications of people

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

Kön

-0.76

︎

-0.62

McE

-0.61

 interpol

-0.60

 sauf

-0.58

Kä

-0.58

뮬

-0.58

 transparence

-0.57

 étoile

-0.57

تح

-0.57

POSITIVE LOGITS

 group

2.76

 groups

2.60

 Groups

2.42

 Group

2.40

group

2.32

 GROUP

2.27

 getGroup

2.25

Group

2.25

groups

2.20

GROUP

2.20

Activations Density 0.139%

mentions of groups and classifications of people

No Comments

No Known Activations