INDEX

Explanations

contractions and negations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 CreateTagHelper

-0.85

RenderAtEndOf

-0.66

LookAnd

-0.66

 InputDecoration

-0.63

Биография

-0.57

bootstrapcdn

-0.57

aarrggbb

-0.56

*/].

-0.54

 Administrativna

-0.54

InputBorder

-0.53

POSITIVE LOGITS

 Hosts

0.34

 обнов

0.33

 hubs

0.33

 Rady

0.33

见状

0.32

 hosts

0.32

Convergence

0.32

✅

0.32

 refreshed

0.32

Generalized

0.32

Activations Density 0.572%

contractions and negations

No Known Activations