INDEX

Explanations

mathematical terminology and concepts related to functions, distributions, and limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للمعارف

-0.54

 manqué

-0.50

setcounter

-0.50

عات

-0.49

 Spin

-0.48

 Refin

-0.48

惯

-0.47

)_/¯

-0.47

 COUN

-0.46

 riesgo

-0.44

POSITIVE LOGITS

ReLU

0.82

GOTREF

0.75

 exponential

0.73

 Exponential

0.72

 sigmoid

0.71

tanh

0.70

 FontWeight

0.68

 expon

0.67

 '\\;'

0.65

exponential

0.64

Activations Density 0.809%

mathematical terminology and concepts related to functions, distributions, and limits

No Comments

No Known Activations