INDEX

Explanations

words and concepts related to familiarity and known experiences

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

 Renoir

-0.74

 springfox

-0.72

 Polyn

-0.71

 Performances

-0.70

 ddelweddau

-0.70

Portály

-0.70

 Cowper

-0.70

mbh

-0.69

 Raptor

-0.68

Abitanti

-0.68

POSITIVE LOGITS

 familiar

1.40

 Familiar

1.32

 familiarity

1.28

familiar

1.27

Familiar

1.24

famili

1.21

 famili

1.07

 Famili

1.06

Famili

1.04

 acquaintance

0.99

Activations Density 0.103%

words and concepts related to familiarity and known experiences

No Comments

No Known Activations