INDEX

Explanations

initials or acronyms within text

oai_token-act-pair · gpt-3.5-turbo

acronyms and abbreviations related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

omorphic

-0.92

istically

-0.88

itatively

-0.83

iary

-0.80

tery

-0.80

iced

-0.78

ically

-0.77

iously

-0.77

sey

-0.77

ices

-0.77

POSITIVE LOGITS

VER

1.27

LL

1.27

VOL

1.26

LECT

1.26

VEL

1.26

VO

1.25

ACH

1.23

VEN

1.22

ASON

1.21

AN

1.21

Activations Density 0.064%

initials or acronyms within text

acronyms and abbreviations related to organizations or entities

No Comments

No Known Activations