INDEX

Explanations

statements related to legal or procedural actions in a court context

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

 itſelf

-2.11

 myſelf

-2.08

Efq

-2.06

 ―――――

-1.80

 Shakspeare

-1.80

 Monfieur

-1.79

 pleaſure

-1.77

 photolibrary

-1.76

 raiſ

-1.74

 Jefus

-1.74

POSITIVE LOGITS

1.31

an

1.25

the

1.24

in

1.22

is

1.18

1.16

1.11

it

1.09

1.07

Activations Density 3.024%

statements related to legal or procedural actions in a court context

No Comments

No Known Activations

statements related to legal or procedural actions in a court context

No Comments

No Known Activations