INDEX

Explanations

terms related to electrical wiring

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Chall

-0.91

ValueStyle

-0.90

appara

-0.85

WebVitals

-0.84

 betweenstory

-0.84

goku

-0.84

SBATCH

-0.83

eneuve

-0.82

 &___

-0.82

Denomin

-0.81

POSITIVE LOGITS

 wire

1.71

 Wire

1.55

wire

1.54

 wires

1.50

Wire

1.46

 Wires

1.37

 WIRE

1.35

 wired

1.26

WIRE

1.26

er

1.17

Activations Density 0.010%

terms related to electrical wiring

No Comments

No Known Activations