INDEX

Explanations

specific names, abbreviations, and terms, possibly related to a particular context or field of interest

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms, particularly relating to positions or titles

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

erity

-0.77

ãĤ¹ãĥĪ

-0.76

adeon

-0.73

 dism

-0.73

Downloadha

-0.69

 Crom

-0.68

tta

-0.66

Â²

-0.66

ielding

-0.63

 reproduce

-0.62

POSITIVE LOGITS

PF

2.88

OT

2.29

OG

1.53

SG

1.19

PTS

1.16

JC

1.08

OL

1.07

EG

1.01

RHP

0.93

PB

0.91

Activations Density 0.018%

specific names, abbreviations, and terms, possibly related to a particular context or field of interest

abbreviations or acronyms, particularly relating to positions or titles

No Known Activations