INDEX

Explanations

elements related to mathematical or computational structures, particularly in the context of equations or algorithms

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

Mathematical symbols/notation

np_acts-logits-general · gemini-2.0-flash

mathematical expressions and code delimiters

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

left

-1.61

 left

-1.24

langle

-1.00

 Left

-0.90

right

-0.90

 LEFT

-0.84

 izquierda

-0.81

LEFT

-0.81

migrationBuilder

-0.80

 esquerda

-0.78

POSITIVE LOGITS

 تانيه

0.54

 fata

0.47

Charset

0.46

colare

0.46

deep

0.46

 ujednoznacz

0.45

]]

0.44

}}

0.43

рыя

0.43

))

0.43

Activations Density 0.552%

elements related to mathematical or computational structures, particularly in the context of equations or algorithms

Mathematical symbols/notation

mathematical expressions and code delimiters

No Comments

No Known Activations