INDEX

Explanations

references to evidence and empirical data

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 useRouter

-0.89

 Obispo

-0.75

expandindo

-0.72

SBATCH

-0.67

ỏa

-0.67

ptonshire

-0.66

✨:

-0.66

Tembelea

-0.65

لاق

-0.64

 Karla

-0.64

POSITIVE LOGITS

evidence

1.49

 Evidence

1.46

 evidence

1.44

 EVIDENCE

1.40

Evidence

1.37

 Evid

1.30

 evidences

1.29

 evidencia

0.99

evid

0.97

 evid

0.95

Activations Density 0.130%

references to evidence and empirical data

No Known Activations