INDEX

Explanations

terms and symbols related to mathematical and statistical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Crows

-0.54

Joc

-0.53

thâu

-0.53

 Royce

-0.53

Cui

-0.52

Susanne

-0.52

 llvm

-0.52

 elétrico

-0.51

Cus

-0.51

 aeroplane

-0.50

POSITIVE LOGITS

Omega

2.89

 Omega

2.68

 omega

2.43

omega

2.30

Ω

2.04

Ω

1.81

ω

1.47

Ω

1.46

 Alpha

1.39

ω

1.33

Activations Density 0.195%

terms and symbols related to mathematical and statistical expressions

No Comments

No Known Activations