INDEX

Explanations

actions and revisions related to learning, questioning, and evaluating information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.40

</em>

-0.39

-0.38

سر

-0.38

to

-0.37

to

-0.37

View

-0.37

glyphicon

-0.36

tem

-0.36

POSITIVE LOGITS

StructEnd

1.24

GEBURTSDATUM

1.21

RenderAtEndOf

1.16

 فريبيس

1.16

 يتيمه

1.15

 незавершена

1.15

 CreateTagHelper

1.15

 تضيفلها

1.12

ArrowToggle

1.12

 للمعارف

1.10

Activations Density 0.359%

actions and revisions related to learning, questioning, and evaluating information

No Comments

No Known Activations