INDEX

Explanations

terms related to cancer types and specific medical conditions

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

-0.47

to

-0.43

ComponentName

-0.42

 stage

-0.41

le

-0.40

“

-0.40

 concerned

-0.39

 person

-0.39

-0.38

POSITIVE LOGITS

XmlAccessorType

1.22

 propOrder

1.00

 <>",

0.96

AndEndTag

0.95

abestanden

0.92

EndContext

0.91

 snippetHide

0.88

ValueStyle

0.87

Lähteet

0.85

 ProtoMessage

0.82

Activations Density 0.885%

terms related to cancer types and specific medical conditions

No Comments

No Known Activations