INDEX

Explanations

terms related to hardware and software upgrades

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

Slf

-0.77

victor

-0.73

Thor

-0.72

 specchio

-0.70

pyplot

-0.70

 saites

-0.69

Intersection

-0.69

inescence

-0.69

ži

-0.68

 tả

-0.68

POSITIVE LOGITS

Upgrade

0.81

 upgrades

0.80

 Upgrade

0.79

 upgrade

0.79

 Kowal

0.77

 upgrading

0.76

 Vinci

0.74

 goud

0.73

 Kupfer

0.71

 upgraded

0.71

Activations Density 0.095%

terms related to hardware and software upgrades

No Comments

No Known Activations