INDEX

Explanations

numbers and numerical values in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

httphttps

-0.95

tvguidetime

-0.84

 >=",

-0.80

 оригіналу

-0.77

بوابة

-0.74

 Roskov

-0.68

 الرياضيه

-0.67

Архівовано

-0.66

jScrollPane

-0.65

 useRouter

-0.65

POSITIVE LOGITS

enderror

0.62

 Rine

0.53

ênio

0.53

CDCl

0.51

{{\

0.50

</b>

0.50

 econômica

0.50

toHexString

0.48

 Seel

0.48

thyst

0.46

Activations Density 0.236%

numbers and numerical values in various contexts

No Comments

No Known Activations