INDEX

Explanations

mentions of the term "Att" at varying levels of emphasis

oai_token-act-pair · gpt-3.5-turbo

references to the term "Att" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.83

FTWARE

-0.81

enegger

-0.80

ktop

-0.75

 Cuomo

-0.74

ORGE

-0.74

BuyableInstoreAndOnline

-0.71

 Giuliani

-0.70

beard

-0.69

assetsadobe

-0.69

POSITIVE LOGITS

ributed

1.25

itudes

1.24

achment

1.23

ainment

1.20

itude

1.20

ention

1.18

ractive

1.16

ension

1.15

ributes

1.15

orneys

1.13

Activations Density 0.015%

mentions of the term "Att" at varying levels of emphasis

references to the term "Att" in various contexts

No Comments

No Known Activations