INDEX

Explanations

conditional statements or scenarios involving potential outcomes

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

 itſelf

-0.62

 ―――――

-0.58

tonsoft

-0.56

 Houſe

-0.54

TestBed

-0.53

 Cæsar

-0.53

 themſelves

-0.52

 myſelf

-0.52

లాలు

-0.52

ערך

-0.52

POSITIVE LOGITS

 nantinya

0.83

 nanti

0.78

 eventual

0.78

到时候

0.77

 eventually

0.75

 blijkt

0.74

 Eventually

0.72

万一

0.72

 unforeseen

0.72

Eventually

0.72

Activations Density 0.226%

conditional statements or scenarios involving potential outcomes

No Comments

No Known Activations