INDEX

Explanations

phrases indicating internal thought processes and contemplative introspection

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

"in [a|the|their|this|other|itself]"

np_acts-logits-general · gemini-2.0-flash

in ways

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

Kaynakça

-0.64

Бахар

-0.63

 ")");

-0.58

ględ

-0.58

UserScript

-0.57

 tanong

-0.56

scalatest

-0.56

 通販

-0.54

__':

-0.54

 estekak

-0.54

POSITIVE LOGITS

 ways

0.89

 times

0.72

 AssemblyProduct

0.65

 WAYS

0.65

 Ways

0.61

 moments

0.60

 maneras

0.58

 society

0.58

ways

0.57

ImageContext

0.55

Activations Density 0.382%

phrases indicating internal thought processes and contemplative introspection

"in [a|the|their|this|other|itself]"

in ways

No Comments

No Known Activations