INDEX

Explanations

potential uncertainty or suggestions in a statement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ollectionView

-1.02

SBATCH

-0.89

ECA

-0.86

quelize

-0.86

 Breen

-0.85

IFA

-0.82

Aun

-0.82

клопе

-0.81

 Placer

-0.81

 syna

-0.79

POSITIVE LOGITS

 might

1.41

 MIGHT

1.37

 Might

1.34

might

1.31

Might

1.27

 would

1.11

 WOULD

1.00

 could

0.99

 COULD

0.90

 Could

0.89

Activations Density 0.040%

potential uncertainty or suggestions in a statement

No Comments

No Known Activations