INDEX

Explanations

terms related to upgrades and improvements 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

stdc

-0.81

 Steff

-0.76

WriteLiteral

-0.76

LLocation

-0.73

IsContent

-0.73

 uParam

-0.72

ản

-0.72

 Fath

-0.71

SceneManagement

-0.71

 Sarg

-0.71

POSITIVE LOGITS

er

0.81

 Cowper

0.78

 Johnstone

0.77

 flexibles

0.70

EOUT

0.69

wój

0.68

Oby

0.67

 duran

0.67

 Cromwell

0.66

 finalised

0.66

Activations Density 0.046%

terms related to upgrades and improvements in various contexts

No Comments

No Known Activations