INDEX

Explanations

proper nouns related to individuals in different fields such as politics, sports, and entertainment

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Appalach

-0.77

 Appalachian

-0.70

 Willow

-0.69

Â·Â·

-0.67

 Misty

-0.67

 Wyoming

-0.67

 Beacon

-0.66

 Lexington

-0.65

 Eliot

-0.65

ModLoader

-0.64

POSITIVE LOGITS

iani

1.18

Ã¡

1.04

ondo

0.98

iano

0.96

Ã³

0.96

vez

0.95

aldi

0.95

lez

0.94

otti

0.94

utsch

0.92

Activations Density 0.209%

proper nouns related to individuals in different fields such as politics, sports, and entertainment

No Comments

No Known Activations