INDEX

Explanations

phrases referring to data processing elements and their relationships in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

hibition

-0.52

Esk

-0.48

duy

-0.47

كه

-0.46

tsky

-0.45

Anh

-0.45

 judgment

-0.45

CLC

-0.45

 lawsuit

-0.45

 starb

-0.45

POSITIVE LOGITS

 فريبيس

0.78

 betweenstory

0.74

 disambiguazione

0.72

 snippetHide

0.70

ługo

0.70

الحياه

0.68

 '\\;'

0.68

يكب

0.66

estacks

0.65

 Lightboxes

0.63

Activations Density 0.493%

phrases referring to data processing elements and their relationships in a dataset

No Comments

No Known Activations