INDEX

Explanations

medical terms related to diseases or conditions

oai_token-act-pair · gpt-3.5-turbo

words related to various scientific and medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

DragonMagazine

-0.86

=~

-0.75

IRD

-0.73

IVERS

-0.72

IDENT

-0.70

edin

-0.70

skirts

-0.69

handle

-0.68

ITNESS

-0.67

PRES

-0.67

POSITIVE LOGITS

 acid

0.98

otine

0.95

tac

0.87

oric

0.83

entric

0.76

actic

0.75

 foul

0.75

trl

0.74

ulous

0.74

eru

0.72

Activations Density 0.028%

medical terms related to diseases or conditions

words related to various scientific and medical terms

No Comments

No Known Activations