INDEX

Explanations

mathematical expressions and notations involving integrals and derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

خص

-0.49

তথ্যসূত্র

-0.49

Clik

-0.48

rikan

-0.48

emily

-0.46

mai

-0.45

 lage

-0.45

XtraReports

-0.44

 mungkin

-0.44

 protoimpl

-0.44

POSITIVE LOGITS

dx

0.87

dz

0.81

dt

0.77

dx

0.77

dq

0.73

dø

0.71

astéroïdes

0.70

0.68

ⅆ

0.66

dy

0.65

Activations Density 0.575%

mathematical expressions and notations involving integrals and derivatives

No Comments

No Known Activations