INDEX

Explanations

descriptions of investigative actions and discovery processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 schloss

-0.56

енча

-0.52

++]=

-0.50

YLON

-0.48

)++;

-0.48

Prepare

-0.47

mares

-0.47

ganu

-0.46

 cité

-0.46

 mAdapter

-0.46

POSITIVE LOGITS

 revealing

0.74

 iprot

0.71

 unlocked

0.67

 unlock

0.66

 unlocking

0.66

contentLoaded

0.65

 ActivatedRoute

0.64

 Trigger

0.63

 trigger

0.63

createComponent

0.61

Activations Density 0.462%

descriptions of investigative actions and discovery processes

No Comments

No Known Activations