INDEX

Explanations

expressions related to need or necessity

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

 themſelves

-0.85

 itſelf

-0.84

XtraEditors

-0.71

 againſt

-0.71

pausal

-0.70

 whoſe

-0.70

 himſelf

-0.69

ſelf

-0.68

 becauſe

-0.68

 myſelf

-0.68

POSITIVE LOGITS

 need

1.35

 needed

1.31

NEED

1.28

 Need

1.23

 NEED

1.23

needed

1.22

 needs

1.18

 NEEDED

1.16

 needing

1.15

need

1.14

Activations Density 0.084%

expressions related to need or necessity

No Comments

No Known Activations