INDEX

Explanations

numerical data or references to quantities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 itſelf

-1.05

Efq

-1.03

ſelf

-0.94

 ་་

-0.94

 Majefty

-0.93

 houſe

-0.92

 purpoſe

-0.90

 Theſe

-0.90

Eſ

-0.88

 pleaſure

-0.87

POSITIVE LOGITS

two

1.09

 three

1.08

 four

0.98

 major

0.86

 main

0.83

 different

0.82

two

0.82

big

0.81

 separate

0.79

 zwei

0.78

Activations Density 0.568%

numerical data or references to quantities

No Comments

No Known Activations