INDEX

Explanations

mathematical expressions and notations related to integrals and stochastic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

GOTREF

-0.61

EndContext

-0.57

awtextra

-0.52

 arşivlendi

-0.51

 Administrativna

-0.49

 OMITBAD

-0.49

usercontent

-0.47

featureID

-0.47

FormTagHelper

-0.47

sidemargin

-0.47

POSITIVE LOGITS

1.34

dx

0.90

dt

0.90

dz

0.82

dh

0.79

dv

0.77

dm

0.76

ds

0.75

dy

0.73

dE

0.73

Activations Density 1.215%

mathematical expressions and notations related to integrals and stochastic processes

No Comments

No Known Activations