INDEX

Explanations

terms related to randomness and stochastic processes

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

"Random" followed by other words

np_acts-logits-general · gemini-2.0-flash

random walk or variable

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

TagMode

-0.70

 متحده

-0.56

 AssemblyCompany

-0.53

letons

-0.51

 unknownFields

-0.51

μφωνα

-0.50

mored

-0.49

роваться

-0.48

 automatisch

-0.48

disposing

-0.48

POSITIVE LOGITS

AccessFile

0.96

 walk

0.78

izer

0.70

walk

0.69

 Walk

0.69

Walk

0.65

Access

0.64

nly

0.63

ize

0.63

 walks

0.60

Activations Density 0.193%

terms related to randomness and stochastic processes

"Random" followed by other words

random walk or variable

No Comments

No Known Activations