INDEX

Explanations

numerical values associated with data parameters

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

NamedQueries

-1.06

ValueStyle

-0.97

ArrowToggle

-0.95

rawDesc

-0.85

 CreateTagHelper

-0.85

참고

-0.82

inctions

-0.82

arakhand

-0.81

ampunk

-0.80

astify

-0.80

POSITIVE LOGITS

 Boek

0.74

 Fenne

0.71

 Thelma

0.69

el

0.68

Vern

0.67

 $("<

0.66

 Bezug

0.64

Cah

0.62

 Prid

0.62

 reac

0.62

Activations Density 0.091%

numerical values associated with data parameters

No Comments

No Known Activations