INDEX

Explanations

references to addresses or address-related concepts

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

Redacción

-0.77

 Leland

-0.74

Kjelder

-0.73

iwa

-0.72

 PyLong

-0.70

 suivants

-0.70

 Pitman

-0.70

phrine

-0.69

 Fland

-0.68

 Mert

-0.67

POSITIVE LOGITS

 Addresses

1.52

 ADDRESS

1.52

Addresses

1.50

 addresses

1.46

 address

1.44

 Address

1.43

address

1.39

addresses

1.37

 getAddress

1.36

Address

1.34

Activations Density 0.047%

references to addresses or address-related concepts

No Comments

No Known Activations