INDEX

Explanations

terms and phrases related to adjustments or modifications

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

imanapun

-0.71

/−

-0.68

 Barker

-0.67

次的

-0.66

(/\

-0.66

WARDS

-0.65

">+

-0.64

beitrag

-0.62

*:

-0.61

loadAll

-0.60

POSITIVE LOGITS

 ADJUST

1.09

Ajust

1.08

Adjust

0.99

 Adjust

0.96

 ajust

0.93

 Adjustment

0.91

 Adjustments

0.89

 Adjusting

0.88

ADJUST

0.88

 adjustments

0.87

Activations Density 0.016%

terms and phrases related to adjustments or modifications

No Comments

No Known Activations