INDEX

Explanations

mathematical symbols and notation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 doubtnut

-1.30

GEBURTSDATUM

-1.27

 myſelf

-1.24

ſelf

-1.22

 itſelf

-1.21

 ſeveral

-1.17

 Diſ

-1.13

 fubject

-1.10

ſelves

-1.09

 poffible

-1.06

POSITIVE LOGITS

0.89

0.83

0.82

0.81

0.78

...

0.75

Activations Density 2.506%

mathematical symbols and notation

No Comments

No Known Activations