INDEX

Explanations

mentions of the word "Att" with different numerical intensities

oai_token-act-pair · gpt-3.5-turbo

references to attachment or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

assetsadobe

-0.87

theless

-0.85

enegger

-0.79

FTWARE

-0.79

ORGE

-0.77

ktop

-0.76

-0.75

 Giuliani

-0.73

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.73

ĸļ

-0.71

POSITIVE LOGITS

itudes

1.24

ributed

1.20

anooga

1.17

itude

1.16

achment

1.15

ribute

1.15

ainment

1.14

ributes

1.14

ention

1.12

ension

1.08

Activations Density 0.011%

mentions of the word "Att" with different numerical intensities

references to attachment or connections

No Comments

No Known Activations