INDEX

Explanations

data points such as numbers and abbreviations in a structured format

oai_token-act-pair · gpt-3.5-turbo

numerical values and references to specific locations or positions

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

 VIDEOS

-0.50

 astronomers

-0.47

 archaeologists

-0.46

 Employees

-0.46

 marriages

-0.46

FAQ

-0.45

 whistleblowers

-0.45

pired

-0.44

pires

-0.43

 Bungie

-0.42

POSITIVE LOGITS

+.

1.49

!.

1.30

$.

1.23

%.

1.21

*.

1.16

.[

1.15

1.10

_.

1.08

.</

1.08

().

1.06

Activations Density 1.004%

data points such as numbers and abbreviations in a structured format

numerical values and references to specific locations or positions

No Comments

No Known Activations