INDEX

Explanations

phrases that express uncertainty or likelihood

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

 movimentos

-0.57

 Golfo

-0.56

 élevées

-0.54

 dance

-0.53

zman

-0.53

-0.52

Learn

-0.52

CHM

-0.52

 Ches

-0.52

POSITIVE LOGITS

 Probably

1.43

 probably

1.40

bably

1.34

 prolly

1.33

Probably

1.29

probably

1.25

 likely

1.12

 Likely

1.06

 perhaps

1.04

rscheinlich

1.01

Activations Density 0.087%

phrases that express uncertainty or likelihood

No Comments

No Known Activations