INDEX

Explanations

assertions and statements that establish the validity of a claim or idea

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

imdi

-0.56

 poffe

-0.52

]--;

-0.51

Ranks

-0.50

Appellants

-0.50

AccessorTable

-0.49

 surprised

-0.48

</tfoot>

-0.48

IonicModule

-0.47

 gespannt

-0.47

POSITIVE LOGITS

 ujednoznacz

0.82

onViewCreated

0.81

EndContext

0.72

 الدولى

0.71

WEBPACK

0.71

 nonatomic

0.69

 consultato

0.66

enumii

0.66

 فريبيس

0.65

setof

0.64

Activations Density 0.063%

assertions and statements that establish the validity of a claim or idea

No Comments

No Known Activations