INDEX

Explanations

phrases related to innovation and creating new things or models

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "newness" or innovation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aminer

-0.77

amus

-0.73

istine

-0.73

ogun

-0.71

yip

-0.70

OPA

-0.69

cius

-0.69

former

-0.68

oche

-0.68

acebook

-0.67

POSITIVE LOGITS

bies

1.46

 entrants

1.30

 arrivals

1.29

 technologies

1.19

 hires

1.16

bie

1.16

 ways

1.15

 developments

1.13

 discoveries

1.11

 recruits

1.10

Activations Density 0.079%

phrases related to innovation and creating new things or models

references to the concept of "newness" or innovation

No Comments

No Known Activations