INDEX

Explanations

phrases that indicate opportunities

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

Negative Logits

 StringVar

-0.80

 Moura

-0.67

tabel

-0.65

 kand

-0.64

 solches

-0.64

 Celery

-0.63

artan

-0.62

mast

-0.62

 sensible

-0.62

compat

-0.61

POSITIVE LOGITS

 Opportunity

1.74

Opportunity

1.71

 opportunity

1.67

 Opportunities

1.62

Opportunities

1.61

 opportunities

1.59

opportunity

1.58

opportunities

1.51

 OPPORTUNITY

1.41

 OPPORTUNITIES

1.38

Activations Density 0.029%

phrases that indicate opportunities

No Known Activations