INDEX

Explanations

percentages and URLs

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

Code and special characters within text

np_acts-logits-general · gemini-2.0-flash

can ignore

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

новниш

-0.63

antMatchers

-0.61

 wireType

-0.58

 propOrder

-0.58

LayoutStyle

-0.57

 ProtoMessage

-0.54

 AssemblyTitle

-0.53

protoc

-0.53

ieson

-0.50

Oneof

-0.50

POSITIVE LOGITS

 viewDidLoad

0.54

CBN

0.54

Lähteet

0.53

 EconPapers

0.53

mV

0.51

XB

0.51

 floods

0.51

CPtr

0.51

Chl

0.47

GV

0.47

Activations Density 0.143%

percentages and URLs

Code and special characters within text

can ignore

No Comments

No Known Activations