INDEX

Explanations

compound words with a hyphen in the middle

oai_token-act-pair · gpt-3.5-turbo

phrases related to negative attributes or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Marketable

-0.72

 Whedon

-0.67

 omission

-0.65

 percept

-0.65

 circumcised

-0.64

İĭ

-0.62

CIS

-0.60

Tig

-0.60

 Salvador

-0.60

HRC

-0.60

POSITIVE LOGITS

based

1.32

level

1.18

grown

1.11

mounted

1.08

goers

1.06

specific

1.03

sized

1.02

derived

1.01

building

1.00

brew

1.00

Activations Density 0.114%

compound words with a hyphen in the middle

phrases related to negative attributes or conditions

No Comments

No Known Activations