INDEX

Explanations

references to workshops and related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

djangoproject

-0.91

ANNELS

-0.74

unmodifiable

-0.72

 numberWith

-0.70

voorbeeld

-0.67

webdriver

-0.67

 Baran

-0.66

Bindable

-0.65

 Nanotechnology

-0.65

++){

-0.64

POSITIVE LOGITS

 workshops

1.96

 workshop

1.87

 Workshop

1.77

 Workshops

1.69

workshop

1.66

 WORKSHOP

1.65

Workshop

1.59

Workshops

1.50

 atelier

1.06

 ateliers

1.02

Activations Density 0.052%

references to workshops and related events

No Comments

No Known Activations