INDEX

Explanations

phrases that highlight significance and necessity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

contentLoaded

-0.80

ISupport

-0.70

kloped

-0.70

SOUNDBITE

-0.64

AddTagHelper

-0.62

styleType

-0.62

 defaultstate

-0.61

LookAnd

-0.60

Personensuche

-0.60

RunWith

-0.59

POSITIVE LOGITS

 factor

0.77

 factors

0.68

íssima

0.67

 ruolo

0.66

 aspect

0.66

 role

0.65

 facteur

0.65

importance

0.64

 importanza

0.63

 faktor

0.63

Activations Density 0.286%

phrases that highlight significance and necessity in various contexts

No Comments

No Known Activations