INDEX

Explanations

technology-related terms and company names

oai_token-act-pair · gpt-3.5-turbo

terms related to technology and innovation in businesses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pardon

-0.87

akespe

-0.76

 wast

-0.75

 hump

-0.75

aeper

-0.74

 eaten

-0.74

 spoken

-0.73

 desper

-0.73

 subp

-0.72

rul

-0.70

POSITIVE LOGITS

 Labs

1.26

 Technologies

1.24

Ltd

1.20

 Networks

1.19

 Corporation

1.11

 Solutions

1.07

 Laboratories

1.06

Corp

1.04

Â®

1.04

 Corp

1.01

Activations Density 0.379%

technology-related terms and company names

terms related to technology and innovation in businesses

No Comments

No Known Activations