INDEX

Explanations

concepts related to diagnostic criteria and mental health

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 utafitiHapana

-1.12

 MainAxisSize

-0.92

webElementXpaths

-0.90

sizeCache

-0.89

 Italijanski

-0.87

tagHelperRunner

-0.86

 OFDb

-0.74

enderror

-0.74

الإنجليزية

-0.74

 Wiktionnaire

-0.73

POSITIVE LOGITS

bibitem

0.45

 ostavi

0.45

ir

0.45

van

0.44

0.43

...

0.42

 venezol

0.42

so

0.41

wij

0.41

 pengh

0.41

Activations Density 0.093%

concepts related to diagnostic criteria and mental health

No Comments

No Known Activations