INDEX

Explanations

terms related to position or control in a legal or regulatory context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

endregion

-0.65

 mangel

-0.65

noons

-0.61

Funciones

-0.60

<?

-0.60

 pamamagitan

-0.60

 behalf

-0.59

 itſelf

-0.57

期刊论文

-0.57

Uninitialized

-0.56

POSITIVE LOGITS

 position

0.95

SourceChecksum

0.73

 positions

0.72

position

0.72

 Position

0.68

Position

0.66

Bronnen

0.60

 Positions

0.60

 POSITION

0.60

 debt

0.59

Activations Density 0.251%

terms related to position or control in a legal or regulatory context

No Comments

No Known Activations