INDEX

Explanations

phrases containing the word "Att", potentially related to a specific person or topic

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "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 @ 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

ktop

-0.67

vous

-0.67

FTWARE

-0.66

 Cuomo

-0.66

 Giuliani

-0.66

theless

-0.64

tics

-0.64

ATING

-0.63

ORGE

-0.63

BuyableInstoreAndOnline

-0.62

POSITIVE LOGITS

ractive

1.33

ention

1.29

itudes

1.28

orneys

1.27

itudinal

1.24

ributes

1.23

ension

1.23

achment

1.22

raction

1.22

itude

1.18

Activations Density 0.026%

phrases containing the word "Att", potentially related to a specific person or topic

mentions of the word "Att" in various contexts

No Comments

No Known Activations