INDEX

Explanations

structured data representations and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

からです

-0.44

 kính

-0.44

omin

-0.43

<eos>

-0.43

Re

-0.40

NameInMap

-0.39

тивен

-0.39

Hil

-0.39

elden

-0.39

per

-0.39

POSITIVE LOGITS

 صوتيه

0.86

principalColumn

0.81

 Monfieur

0.80

 Paglinawan

0.74

 defStyleAttr

0.72

aarrggbb

0.72

orsese

0.71

 GeoNames

0.69

 Jefus

0.68

 chinoise

0.68

Activations Density 0.377%

structured data representations and definitions

No Comments

No Known Activations