INDEX

Explanations

references to legal cases and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

</b>

-1.02

</i>

-0.93

Gew

-0.89

”

-0.85

-0.81

.”

-0.78

“

-0.77

”.

-0.77

par

-0.76

POSITIVE LOGITS

^(@)

1.33

 myſelf

1.31

 Monfieur

1.24

 uſed

1.22

 iſt

1.20

 Anſ

1.19

 pleaſure

1.17

 Majefty

1.14

 Jefus

1.13

 répon

1.12

Activations Density 1.629%

references to legal cases and related terminology

No Comments

No Known Activations