INDEX

Explanations

references to additional components or features in a technical context

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

 memen

-0.44

 early

-0.44

 Sand

-0.42

òria

-0.40

-0.39

vor

-0.39

råd

-0.39

Bo

-0.39

 explicó

-0.39

POSITIVE LOGITS

RenderAtEndOf

1.00

migrationBuilder

0.86

 betweenstory

0.84

TintMode

0.80

 تانيه

0.76

 disambiguazione

0.75

 Bourgoin

0.68

 zase

0.67

 ditto

0.67

 ANOTHER

0.66

Activations Density 0.514%

references to additional components or features in a technical context

No Comments

No Known Activations