INDEX

Explanations

acronyms related to medical conditions

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms related to scientific or technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

\'

-0.87

Downloadha

-0.81

uyomi

-0.80

wagen

-0.76

EStream

-0.75

assetsadobe

-0.74

 gorilla

-0.73

awaru

-0.69

omorphic

-0.68

flies

-0.67

POSITIVE LOGITS

OF

1.10

Ds

1.08

IS

1.07

NP

1.06

FS

1.04

1.03

MN

1.00

ES

1.00

ND

0.99

0.98

Activations Density 0.105%

acronyms related to medical conditions

abbreviations or acronyms related to scientific or technical terms

No Comments

No Known Activations