INDEX

Explanations

medical terms and procedures related to imaging and treatment

oai_token-act-pair · gpt-3.5-turbo

terms related to medical imaging and treatment methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wonderland

-0.71

 Abbey

-0.70

lvl

-0.69

 Birthday

-0.68

 Yard

-0.67

 Stud

-0.67

 Grounds

-0.66

lished

-0.66

 Rowling

-0.65

Blog

-0.65

POSITIVE LOGITS

 antibodies

1.11

oxide

1.08

oxin

1.03

ethyl

1.00

 toxins

0.99

 radiation

0.98

rosis

0.97

 polymer

0.97

 toxin

0.96

 hydro

0.95

Activations Density 0.693%

medical terms and procedures related to imaging and treatment

terms related to medical imaging and treatment methods

No Comments

No Known Activations