INDEX

Explanations

terms and references related to scientific functions and roles 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.97

 avoient

-0.83

 auroit

-0.82

المكان

-0.81

 ainfi

-0.80

 feroit

-0.79

 sauvages

-0.77

 avoit

-0.76

rrggbb

-0.74

 pouvoit

-0.74

POSITIVE LOGITS

0.51

 notable

0.49

Den

0.46

inf

0.46

 core

0.46

Bes

0.45

Gemeinden

0.44

tez

0.44

os

0.44

Activations Density 0.537%

terms and references related to scientific functions and roles in various contexts

No Comments

No Known Activations