INDEX

Explanations

terms related to medical conditions and criteria for study eligibility

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

 domes

-0.60

 conten

-0.52

hető

-0.51

lats

-0.47

CONT

-0.44

Спо

-0.44

 algo

-0.44

ær

-0.44

 Residual

-0.44

planes

-0.44

POSITIVE LOGITS

ActionCreators

0.87

Hochspringen

0.81

таратура

0.80

 صوتيه

0.78

 propOrder

0.78

 predeceased

0.74

⋙

0.73

TargetException

0.73

Välislingid

0.72

XmlAccessorType

0.71

Activations Density 0.009%

terms related to medical conditions and criteria for study eligibility

No Comments

No Known Activations