INDEX

Explanations

organizations and groups

oai_token-act-pair · gpt-3.5-turbo

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

orthy

-0.80

ãĤĵ

-0.73

 nonex

-0.73

-|

-0.68

################

-0.67

endon

-0.65

inct

-0.64

speech

-0.64

à¼

-0.63

ouple

-0.63

POSITIVE LOGITS

USS

0.96

 Canaver

0.82

HMS

0.80

 responsible

0.79

 Garry

0.78

Phi

0.78

 Gale

0.77

 Samar

0.77

 Huntington

0.76

 Greenberg

0.76

Activations Density 0.370%

organizations and groups

No Comments

No Known Activations