INDEX

Explanations

references to judges and the act of judging or related terminology

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 tạp

-0.67

</em>

-0.65

 Carmichael

-0.62

お勧め

-0.62

zí

-0.60

 raisons

-0.60

tbx

-0.59

 Carlyle

-0.58

星人

-0.58

RIK

-0.56

POSITIVE LOGITS

 judges

1.60

jud

1.59

 Judges

1.53

JUD

1.51

JUDGE

1.37

 judge

1.35

 JUDGE

1.35

jud

1.35

Judge

1.31

Judges

1.30

Activations Density 0.097%

references to judges and the act of judging or related terminology

No Comments

No Known Activations