INDEX

Explanations

programming-related terms and functions

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

Code snippets or error messages

np_acts-logits-general · gemini-2.0-flash

Jay, absence of

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

riture

-0.60

 Ibidem

-0.58

تقاوى

-0.57

adpleegd

-0.56

 garcía

-0.54

cedures

-0.53

lua

-0.53

zędu

-0.53

didSet

-0.52

 (…)

-0.51

POSITIVE LOGITS

 lakhs

0.63

 Maruti

0.58

 upto

0.56

లాలు

0.56

Marks

0.55

 saree

0.53

 lakh

0.53

 regno

0.53

Pvt

0.53

Jain

0.53

Activations Density 0.044%

programming-related terms and functions

Code snippets or error messages

Jay, absence of

No Comments

No Known Activations