INDEX

Explanations

references to the word "back" and its context across different usages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Larsen

-0.91

°•

-0.88

%)$

-0.86

tershire

-0.85

__":

-0.84

••••

-0.81

 Winaray

-0.79

Gemeinden

-0.77

ряда

-0.77

urethane

-0.77

POSITIVE LOGITS

Back

1.35

 Back

1.32

BACK

1.30

back

1.30

 BACK

1.23

 back

1.22

 backs

1.13

backs

1.02

 indietro

1.00

 Backman

1.00

Activations Density 0.076%

references to the word "back" and its context across different usages

No Comments

No Known Activations