INDEX

Explanations

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 للاسماء

-0.95

featureID

-0.86

 Wikimedijinoj

-0.82

AsUp

-0.81

 ſche

-0.79

LabelTagHelper

-0.77

uxxxx

-0.77

المناصب

-0.76

 ſever

-0.76

msgTypes

-0.74

POSITIVE LOGITS

</h5>

0.58

 disponibilités

0.48

 Culture

0.45

Van

0.43

Culture

0.43

</h4>

0.43

Lar

0.41

なもの

0.40

StandardCharsets

0.40

 fool

0.40

Activations Density 0.373%

numerical data and statistics

No Comments

No Known Activations