INDEX

Explanations

numerical values and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 invité

-0.42

 singoli

-0.41

 coût

-0.40

 Lump

-0.40

agio

-0.39

 peur

-0.38

 lisäksi

-0.38

 Buen

-0.38

 judiciales

-0.38

 rús

-0.37

POSITIVE LOGITS

 None

1.21

 none

1.18

None

1.13

 correct

1.03

 Correct

1.02

none

0.99

 option

0.97

 options

0.96

Correct

0.96

 NONE

0.95

Activations Density 0.629%

numerical values and mathematical expressions

No Comments

No Known Activations