INDEX

Explanations

references to regulation or regulatory frameworks

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

and tokens starting with "reg"

np_acts-logits-general · gemini-2.0-flash

regulating or regressive

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

pernic

-0.51

 piaci

-0.49

ennom

-0.47

 تضيفلها

-0.46

 Permanente

-0.46

quitous

-0.46

 Bantu

-0.44

 fallu

-0.44

 Moha

-0.44

 Beren

-0.44

POSITIVE LOGITS

ulating

0.68

ulative

0.66

ulators

0.64

ulat

0.63

ulate

0.62

 ular

0.60

AndEndTag

0.59

 typelib

0.59

complexContent

0.58

RegressionTest

0.56

Activations Density 0.167%

references to regulation or regulatory frameworks

and tokens starting with "reg"

regulating or regressive

No Comments

No Known Activations