INDEX

Explanations

terms related to veterinary medicine and animal care

oai_token-act-pair · gpt-3.5-turbo

terms related to veterinary and animal welfare

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

ulative

-0.73

annis

-0.72

ijn

-0.69

ibur

-0.69

icity

-0.68

ysc

-0.68

inders

-0.67

asar

-0.66

 Madden

-0.66

 Morrow

-0.64

POSITIVE LOGITS

 veterin

1.06

vet

0.98

 veterinary

0.97

 veterinarian

0.96

 puppies

0.94

 Humane

0.93

 euth

0.92

 animals

0.91

 Breed

0.89

 dogs

0.88

Activations Density 0.060%

terms related to veterinary medicine and animal care

terms related to veterinary and animal welfare

No Comments

No Known Activations