INDEX

Explanations

notable categories and identifiers in legal or official documents

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

-0.75

 fieldNum

-0.72

 NSCoder

-0.66

oredCriteria

-0.65

kháu

-0.65

 typelib

-0.63

AndEndTag

-0.62

 ویکی‌پدی

-0.60

UnsafeEnabled

-0.60

المصادر

-0.59

POSITIVE LOGITS

0.82

0.60

ResumeLayout

0.51

0.48

orteur

0.47

0.46

 valla

0.46

ochem

0.44

intos

0.43

Activations Density 0.152%

notable categories and identifiers in legal or official documents

No Comments

No Known Activations