INDEX

Explanations

specific percentage values mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Efq

-0.90

ſelf

-0.87

 houſe

-0.87

 Monfieur

-0.86

 pleaſure

-0.84

 uſe

-0.83

 Anſ

-0.82

 Perſ

-0.81

 Reſ

-0.81

 Majefty

-0.80

POSITIVE LOGITS

 cent

2.79

 Cent

2.02

cent

1.96

Cent

1.95

 CENT

1.52

CENT

1.25

 cents

1.21

 Centurion

1.10

 Centennial

1.05

 cento

0.99

Activations Density 0.085%

specific percentage values mentioned in the text

No Comments

No Known Activations