INDEX

Explanations

keywords related to technical processes or configurations in a computing or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 EconPapers

-0.70

Jereo

-0.62

Referanser

-0.53

Swal

-0.50

theless

-0.50

IFI

-0.48

skraft

-0.48

momix

-0.48

outheast

-0.47

renta

-0.47

POSITIVE LOGITS

 behalf

1.36

 basis

0.98

 occasion

0.86

 occasions

0.82

 ועל

0.79

basis

0.78

 وعلى

0.73

Basis

0.67

 otomatig

0.65

 grounds

0.65

Activations Density 0.427%

keywords related to technical processes or configurations in a computing or scientific context

No Comments

No Known Activations