INDEX

Explanations

references to Oracle and related entities, especially in the context of research or technology

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

Oxid

-0.80

Gon

-0.73

pidou

-0.73

Jem

-0.71

 Calabria

-0.70

PIN

-0.70

PIO

-0.70

UTM

-0.69

 Kidd

-0.69

 Rodrig

-0.68

POSITIVE LOGITS

SequentialGroup

0.85

 объя

0.83

 Noyes

0.82

 Tent

0.81

GIVEREF

0.78

 Chester

0.76

 tents

0.74

AndEndTag

0.73

oracle

0.73

 Watson

0.73

Activations Density 1.361%

references to Oracle and related entities, especially in the context of research or technology

No Comments

No Known Activations