INDEX

Explanations

numerical data or references within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

StrictEqual

-0.53

相

-0.46

LabelTagHelper

-0.41

])),

-0.41

 indi

-0.41

TagMode

-0.41

ORETICAL

-0.40

 Brake

-0.39

in

-0.38

aan

-0.38

POSITIVE LOGITS

Datuak

0.77

etc

0.76

expandindo

0.75

Etc

0.75

 ویکی‌پدیای

0.75

AnimationsModule

0.71

Etc

0.70

etc

0.70

Портали

0.70

IntoConstraints

0.70

Activations Density 0.413%

numerical data or references within a context

No Comments

No Known Activations