INDEX

Explanations

references to rankings and positions in a list

oai_token-act-pair · gpt-3.5-turbo

references to ranking or positional status in lists or hierarchies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ufact

-0.75

Äĩ

-0.69

ajor

-0.67

Mub

-0.66

cci

-0.65

 Lauder

-0.65

ATIONS

-0.63

 Griffith

-0.62

ustom

-0.60

_-

-0.60

POSITIVE LOGITS

most

1.18

ographical

1.10

 tier

1.00

ography

1.00

deck

0.96

 drawer

0.94

 scorer

0.93

ographic

0.90

eka

0.88

liest

0.88

Activations Density 0.034%

references to rankings and positions in a list

references to ranking or positional status in lists or hierarchies

No Comments

No Known Activations