INDEX

Explanations

specific references to medical institutions, practices, or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

webElementXpaths

-0.60

 conséquent

-0.44

 cetera

-0.42

جمعیت

-0.42

ModelAdmin

-0.41

 barat

-0.41

یم

-0.40

Rujukan

-0.39

ample

-0.39

RenderAtEndOf

-0.39

POSITIVE LOGITS

gonic

0.70

ValueStyle

0.67

CMY

0.65

 useStyles

0.62

 OFDb

0.62

 otomatig

0.62

出版年

0.62

RTSN

0.62

 صوتيه

0.62

cfs

0.61

Activations Density 0.713%

specific references to medical institutions, practices, or standards

No Comments

No Known Activations