INDEX

Explanations

terms related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to technology and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Bett

-0.96

 Duchess

-0.95

 thous

-0.89

 Johann

-0.87

 Kendall

-0.83

Joh

-0.81

Jenn

-0.80

 Dillon

-0.79

 Merrill

-0.79

 Wyatt

-0.78

POSITIVE LOGITS

 Electrical

0.94

 electricity

0.93

 cyber

0.93

 physic

0.93

 broadband

0.91

 telecommunications

0.90

gas

0.89

radio

0.89

gas

0.88

computer

0.88

Activations Density 0.403%

terms related to geographical locations

specific names or terms related to technology and media

No Comments

No Known Activations