INDEX

Explanations

terms related to theatrical production and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 myſelf

-1.61

 itſelf

-1.54

 ſeveral

-1.43

ſelf

-1.40

 Majefty

-1.40

 Jefus

-1.40

 themſelves

-1.39

 himſelf

-1.36

ſelves

-1.33

 uſed

-1.30

POSITIVE LOGITS

vs

0.63

 mennes

0.52

wy

0.48

vy

0.48

vp

0.48

vn

0.48

 accidentes

0.46

eu

0.46

 entende

0.44

Activations Density 0.056%

terms related to theatrical production and performance

No Comments

No Known Activations