INDEX

Explanations

occurrences of the abbreviation "SHA" and related terms in cryptographic contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 يتيمه

-0.94

 CiNii

-0.85

ंदीखरीदारी

-0.77

"}")

-0.77

 الحره

-0.72

GeoNames

-0.72

VersionUID

-0.70

dafx

-0.69

 BoxFit

-0.68

POSITIVE LOGITS

sha

1.19

Sha

1.04

sha

0.94

Sha

0.86

SHA

0.85

 shaded

0.79

 shading

0.73

 Sham

0.70

Sham

0.68

SHA

0.68

Activations Density 0.050%

occurrences of the abbreviation "SHA" and related terms in cryptographic contexts

No Known Activations