INDEX

Explanations

occurrences of the letter "A" in various contexts

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

vig

-0.76

 investi

-0.72

 esper

-0.71

 impact

-0.69

 vider

-0.69

kti

-0.68

 indepen

-0.68

 kari

-0.68

 Seung

-0.67

 Island

-0.67

POSITIVE LOGITS

getA

1.33

1.31

1.11

aA

1.00

dA

0.92

QApplication

0.90

 brancas

0.90

 scaricare

0.87

0.86

Activations Density 0.429%

occurrences of the letter "A" in various contexts

No Comments

No Known Activations