INDEX

Explanations

questions and answers that explore personal experiences and opinions

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

 Majefty

-1.11

Efq

-1.00

ſelf

-1.00

 myſelf

-0.98

 Monfieur

-0.93

 ſtate

-0.93

 Jefus

-0.92

 Perſ

-0.88

 Shakspeare

-0.87

 itſelf

-0.85

POSITIVE LOGITS

 convertView

0.50

reg

0.45

XmlEnum

0.40

reg

0.39

 mergeFrom

0.39

 primas

0.39

um

0.39

If

0.38

lunda

0.38

 pull

0.38

Activations Density 0.517%

questions and answers that explore personal experiences and opinions

No Comments

No Known Activations