INDEX

Explanations

references to sensors

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

 SENSE

-1.12

 Sense

-0.93

 sense

-0.89

sense

-0.88

 Stande

-0.77

 useStyles

-0.74

 useNavigate

-0.74

***/

-0.74

RISE

-0.73

 makeStyles

-0.71

POSITIVE LOGITS

 sensors

0.94

 Sensors

0.92

Sensors

0.88

sensors

0.88

 Lawton

0.81

 оригіналу

0.74

 sensor

0.73

cautionary

0.71

ensors

0.70

Sensor

0.69

Activations Density 0.004%

references to sensors

No Comments

No Known Activations

references to sensors

No Comments

No Known Activations