INDEX

Explanations

references to prescription medications

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prescription" and related terms in medical contexts

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

semble

-0.93

iland

-0.86

aday

-0.85

ochet

-0.83

auga

-0.82

asta

-0.82

atan

-0.81

ashington

-0.73

mite

-0.73

estones

-0.72

POSITIVE LOGITS

 medications

1.09

 medication

1.06

 opioids

1.01

 prescription

1.00

 medicines

0.99

 drugs

0.99

 prescriptions

0.90

 opioid

0.89

 pills

0.86

 drug

0.84

Activations Density 0.015%

references to prescription medications

instances of the word "prescription" and related terms in medical contexts

No Comments

No Known Activations