INDEX

Explanations

mentions of research papers or articles

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

"this paper" or reference to a paper

np_acts-logits-general · gemini-2.0-flash

this paper

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

squareup

-0.49

prepareStatement

-0.48

 للاسماء

-0.47

setVerticalGroup

-0.47

 cucchiai

-0.47

├

-0.46

orghini

-0.44

 Dostupné

-0.43

ftagPool

-0.43

ContentAsync

-0.43

POSITIVE LOGITS

 paper

1.90

paper

1.47

 Paper

1.30

Paper

1.26

 PAPER

1.24

 article

1.14

 papers

1.10

PAPER

1.07

 papir

1.00

 talk

0.95

Activations Density 0.487%

mentions of research papers or articles

"this paper" or reference to a paper

this paper

No Comments

No Known Activations