INDEX

Explanations

mentions of medical terms and practices

oai_token-act-pair · gpt-3.5-turbo

references to medicine and medical practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 sqor

-0.76

icker

-0.73

iannopoulos

-0.68

adia

-0.67

ymm

-0.66

etime

-0.64

İ

-0.64

 Territories

-0.64

sequence

-0.63

iger

-0.63

POSITIVE LOGITS

 practitioner

0.99

 cures

0.98

 practitioners

0.96

utical

0.94

utics

0.89

istry

0.88

 prescribing

0.88

aceutical

0.86

 dispens

0.83

 cabinets

0.82

Activations Density 0.052%

mentions of medical terms and practices

references to medicine and medical practices

No Comments

No Known Activations