INDEX

Explanations

expressions related to medical or legal evaluations and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.90

 Roskov

-0.84

ArgsConstructor

-0.82

 <>",

-0.79

onViewCreated

-0.79

RegressionTest

-0.78

XmlAccessorType

-0.77

endphp

-0.75

 kasarigan

-0.74

GOTREF

-0.73

POSITIVE LOGITS

 there

0.71

有一个

0.69

有着

0.68

 having

0.66

有一個

0.66

 memiliki

0.66

有了

0.65

 punya

0.65

 има

0.64

 obtenir

0.62

Activations Density 0.408%

expressions related to medical or legal evaluations and their implications

No Comments

No Known Activations