INDEX

Explanations

references to academic sources and citations

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

Text or links within brackets

np_acts-logits-general · gemini-2.0-flash

arXiv papers and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 grazia

-0.56

jooq

-0.55

 voyons

-0.49

XCTAssert

-0.48

 sepol

-0.48

 debió

-0.47

 couverts

-0.46

PLIC

-0.46

 <>",

-0.45

mgang

-0.44

POSITIVE LOGITS

arXiv

1.22

 arXiv

0.95

abestanden

0.91

 EconPapers

0.89

 arxiv

0.69

pdf

0.67

arxiv

0.66

twimg

0.64

 ujednoznacz

0.63

 preprint

0.61

Activations Density 0.107%

references to academic sources and citations

Text or links within brackets

arXiv papers and references

No Comments

No Known Activations