INDEX

Explanations

data related to assessments, evaluations, or criteria for inclusion in studies

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

-1.17

-1.16

<eos>

-1.03

-1.02

in

-0.97

↵↵

-0.94

is

-0.92

-0.91

↵

-0.87

...

-0.87

POSITIVE LOGITS

 itſelf

1.66

 myſelf

1.63

 ―――――

1.53

 Савезне

1.46

 Paglinawan

1.43

Efq

1.43

ſelves

1.41

 Reſ

1.39

 kaarangay

1.38

 Jefus

1.36

Activations Density 1.858%

data related to assessments, evaluations, or criteria for inclusion in studies

No Comments

No Known Activations