INDEX

Explanations

references to specific scientific concepts and classifications related to health and diseases

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

-0.78

</blockquote>

-0.65

</h3>

-0.62

en

-0.57

and

-0.55

</em>

-0.55

POSITIVE LOGITS

 Wikimedijinoj

1.26

تقاوى

1.08

 wikipagina

1.06

 صوتيه

1.02

ftagPool

1.01

 Савезне

0.98

Portály

0.98

Hochspringen

0.97

RenderAtEndOf

0.96

IGraphics

0.96

Activations Density 2.046%

references to specific scientific concepts and classifications related to health and diseases

No Comments

No Known Activations