INDEX

Explanations

symbols and expressions commonly used in mathematical or scientific contexts, particularly in statistical and probabilistic frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.67

inib

-0.64

 referenties

-0.60

createCanvas

-0.57

 anthropo

-0.56

reuung

-0.56

tième

-0.55

 Frist

-0.53

헌

-0.53

tou

-0.52

POSITIVE LOGITS

 LIABLE

0.63

MessageTagHelper

0.61

 生命周期

0.56

MethodManager

0.55

GEBURTSDATUM

0.55

nalités

0.55

 MainAxisSize

0.55

 Pfeffer

0.55

 heapq

0.53

Pautan

0.53

Activations Density 0.906%

symbols and expressions commonly used in mathematical or scientific contexts, particularly in statistical and probabilistic frameworks

No Comments

No Known Activations