INDEX

Explanations

names of political figures

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

Seattle

-0.75

erest

-0.71

 ster

-0.70

 pregn

-0.70

 Poles

-0.69

 Wilmington

-0.68

fecture

-0.68

ppel

-0.66

 glim

-0.64

LCS

-0.64

POSITIVE LOGITS

uddin

1.68

 Hussain

1.45

ullah

1.41

 Khan

1.39

 Ahmad

1.38

 Mahm

1.38

 Sharif

1.38

 Sheikh

1.37

 Ahmed

1.35

ibn

1.35

Activations Density 0.290%

names of political figures

No Comments

No Known Activations