INDEX

Explanations

references to quantum concepts and terminology

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

GenerationType

-0.78

</i>

-0.75

ي

-0.72

PullParser

-0.72

off

-0.72

IOException

-0.70

[]:

-0.69

manfaat

-0.68

ิลปะ

-0.68

 TMPro

-0.67

POSITIVE LOGITS

Qu

1.12

Qu

1.05

 Pequ

1.03

Kv

0.92

 McQu

0.90

QU

0.86

ally

0.84

 Antiqu

0.83

 Quaker

0.83

lingu

0.82

Activations Density 0.533%

references to quantum concepts and terminology

No Comments

No Known Activations