INDEX

Explanations

terms related to medical or biological concepts and strategies for improving health outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 kaarangay

-1.13

SourceChecksum

-1.13

parsedMessage

-1.11

󠁿

-1.10

thâu

-1.08

 Numerade

-1.07

CppMethod

-1.06

 Савезне

-1.06

endphp

-1.05

HtmlAttribute

-1.03

POSITIVE LOGITS

0.56

0.51

<eos>

0.51

0.49

0.48

0.47

0.46

Activations Density 4.082%

terms related to medical or biological concepts and strategies for improving health outcomes

No Comments

No Known Activations