INDEX

Explanations

terms related to accuracy and correctness in information

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

correctness or accuracy

np_acts-logits-general · gemini-2.0-flash

correct or incorrect judgment

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tagHelperRunner

-0.68

 aufnehmen

-0.65

ISODE

-0.63

 existência

-0.63

 חיצוניים

-0.61

 GoogleFonts

-0.61

($__

-0.59

Alf

-0.58

 parlant

-0.57

AnchorStyles

-0.57

POSITIVE LOGITS

 AssemblyCulture

0.75

 Mistake

0.69

 错误

0.67

 Accurate

0.65

 Incorrect

0.64

 accuracy

0.64

 PyLong

0.64

rungsseite

0.63

 precision

0.62

错误

0.62

Activations Density 0.250%

terms related to accuracy and correctness in information

correctness or accuracy

correct or incorrect judgment

No Comments

No Known Activations