INDEX

Explanations

words related to specific physical locations or services

oai_token-act-pair · gpt-3.5-turbo

terms associated with physical locations or settings

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

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

VIDIA

-0.79

 Marketable

-0.74

terday

-0.71

atron

-0.69

 Mehran

-0.69

peria

-0.66

ï¸ı

-0.63

 Castro

-0.63

actionDate

-0.63

WHO

-0.63

POSITIVE LOGITS

 layouts

1.06

 layout

1.03

wide

1.03

mates

0.93

 dwell

0.92

 closures

0.91

 mates

0.89

mate

0.88

 etiquette

0.87

 renovations

0.86

Activations Density 0.563%

words related to specific physical locations or services

terms associated with physical locations or settings

No Comments

No Known Activations