INDEX

Explanations

various mathematical operations and notations

oai_token-act-pair · gpt-3.5-turbo

mathematical formulas and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ingers

-0.70

 nods

-0.68

ersen

-0.67

 cracks

-0.62

ensive

-0.62

 unmist

-0.61

idelines

-0.60

irie

-0.60

 failings

-0.59

iliated

-0.59

POSITIVE LOGITS

sq

1.26

(-

1.23

((

1.18

((

1.16

[(

1.16

 âĪ

1.15

(-

1.05

1.03

1.02

Ï

1.01

Activations Density 0.073%

various mathematical operations and notations

mathematical formulas and expressions

No Comments

No Known Activations