INDEX

Explanations

mentions related to locations or events

oai_token-act-pair · gpt-3.5-turbo

key terms and phrases related to events, organizations, and industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

selage

-0.76

ensical

-0.74

 arsen

-0.65

 lying

-0.65

amous

-0.63

oteric

-0.63

lycer

-0.63

 staggered

-0.61

bestos

-0.61

 reason

-0.61

POSITIVE LOGITS

LLC

1.23

Inc

1.16

Ltd

1.09

 Solutions

1.08

âĦ¢

1.02

 Magazine

0.96

Â®

0.96

LTD

0.90

Magazine

0.89

Org

0.89

Activations Density 0.740%

mentions related to locations or events

key terms and phrases related to events, organizations, and industries

No Comments

No Known Activations