INDEX

Explanations

terms related to laboratory procedures and medical assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

LLocation

-0.66

 дописавши

-0.59

 Biôgrafia

-0.58

Bissau

-0.56

providedIn

-0.56

 snippetHide

-0.56

 Untold

-0.56

 optimisation

-0.56

uisine

-0.55

EndTag

-0.54

POSITIVE LOGITS

smithy

0.59

 severity

0.54

TypedDataSet

0.52

CWE

0.51

Severity

0.50

 recovery

0.49

 Severity

0.49

0.48

severity

0.47

indakan

0.47

Activations Density 1.969%

terms related to laboratory procedures and medical assessments

No Comments

No Known Activations