INDEX

Explanations

references to Korea and Korean-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

VersionUID

-0.74

ValueStyle

-0.57

Legături

-0.55

 tril

-0.51

homonymie

-0.51

winston

-0.51

 كورة

-0.50

 trast

-0.50

Personensuche

-0.49

icose

-0.48

POSITIVE LOGITS

и

1.14

і

0.83

ї

0.80

inafter

0.78

И

0.74

>{@

0.70

MergeFrom

0.69

ить

0.64

 Roskov

0.64

类

0.63

Activations Density 0.097%

references to Korea and Korean-related terms

No Comments

No Known Activations