INDEX

Explanations

specific technical terms related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}}}}

-0.47

</u>

-0.46

he

-0.45

hy

-0.45

ian

-0.45

 freno

-0.44

</i>

-0.44

šek

-0.44

之以

-0.44

tel

-0.44

POSITIVE LOGITS

 للمعارف

1.11

IntoConstraints

1.09

脚注の使い方

1.07

ReusableCell

1.02

 betweenstory

0.97

HasAnnotation

0.96

GEBURTSDATUM

0.95

URLException

0.94

complexContent

0.93

+#+#

0.92

Activations Density 0.619%

specific technical terms related to programming and data structures

No Comments

No Known Activations