INDEX

Explanations

company names or entities

oai_token-act-pair · gpt-3.5-turbo

corporate entities and related business activities

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

qqa

-0.77

genre

-0.75

ydia

-0.72

liest

-0.70

irlf

-0.69

alist

-0.67

req

-0.67

olated

-0.65

idency

-0.65

 Leia

-0.64

POSITIVE LOGITS

 Holdings

1.37

 Corporation

1.33

 Corp

1.31

Ltd

1.28

 subsidiary

1.23

 Industries

1.14

 Technologies

1.13

Inc

1.10

 Laboratories

1.08

 Pharmaceutical

1.07

Activations Density 0.296%

company names or entities

corporate entities and related business activities

No Comments

No Known Activations