INDEX

Explanations

terms related to the experience of suffering or negative health conditions

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

Lyn

-0.83

abetes

-0.80

cencia

-0.78

Datuak

-0.75

EoL

-0.74

Zam

-0.73

 directorio

-0.73

bootstrapcdn

-0.71

]^

-0.69

POSITIVE LOGITS

 Suffer

1.19

 sufferer

0.97

 sufferings

0.96

 sufferers

0.90

 sufren

0.89

suffering

0.86

 suffer

0.83

 suffers

0.81

 suffered

0.80

 Suffering

0.78

Activations Density 0.008%

terms related to the experience of suffering or negative health conditions

No Comments

No Known Activations