INDEX

Explanations

terms related to losses or defeats in competitive situations

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

󠁢

-0.60

rungsseite

-0.59

⇑

-0.57

 ['./

-0.56

 lenker

-0.55

 Doub

-0.52

philo

-0.52

TagMode

-0.50

 cloud

-0.48

trak

-0.48

POSITIVE LOGITS

 défaite

0.66

Losing

0.62

 Désolé

0.61

 defeats

0.61

 verlieren

0.60

 defeat

0.59

 metropolitana

0.59

mbalikan

0.59

 CreateTagHelper

0.57

 esternos

0.57

Activations Density 0.047%

terms related to losses or defeats in competitive situations

No Comments

No Known Activations