INDEX

Explanations

references to fashion models and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ähän

-0.55

inerja

-0.52

vernote

-0.52

rxjs

-0.51

aksanaan

-0.51

 plafond

-0.51

ObjectMeta

-0.49

 AssemblyCompany

-0.49

ionView

-0.48

ThroughAttribute

-0.48

POSITIVE LOGITS

 model

2.75

 models

2.60

model

2.49

 Model

2.49

 Models

2.43

 MODEL

2.38

Model

2.35

 modeling

2.29

 MODELS

2.26

models

2.24

Activations Density 0.122%

references to fashion models and their activities

No Comments

No Known Activations