INDEX

Explanations

conditional phrases and scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

them

-0.63

 Saxons

-0.55

〃

-0.54

 sobą

-0.53

 Lightboxes

-0.53

 honom

-0.52

 prolly

-0.50

ihn

-0.50

 gärna

-0.50

bewerken

-0.50

POSITIVE LOGITS

 there

1.24

 they

1.10

the

0.99

we

0.94

 neither

0.93

 none

0.84

 AssemblyTitle

0.83

 either

0.82

 someone

0.82

it

0.80

Activations Density 0.362%

conditional phrases and scenarios

No Comments

No Known Activations