INDEX

Explanations

references to evidence and its quality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

expandindo

-0.92

lidays

-0.75

 RouterModule

-0.75

Xna

-0.73

Tembelea

-0.73

ertale

-0.73

ptonshire

-0.72

 useRouter

-0.70

 चुनें

-0.68

ỏa

-0.68

POSITIVE LOGITS

 evidence

2.07

evidence

2.04

 Evidence

2.00

 EVIDENCE

1.91

Evidence

1.90

 evidences

1.83

 Evid

1.61

 evidencia

1.32

 evid

1.25

evid

1.24

Activations Density 0.160%

references to evidence and its quality in various contexts

No Comments

No Known Activations