INDEX

Explanations

phrases related to medical prescriptions or prescribing behaviors

oai_token-act-pair · gpt-3.5-turbo

terms related to the prescription of medications

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

 Strait

-0.79

 Gutenberg

-0.78

iland

-0.76

 Stronghold

-0.74

itect

-0.71

Atl

-0.70

Thom

-0.68

uble

-0.66

athan

-0.66

rina

-0.66

POSITIVE LOGITS

 prescribe

1.12

 prescribing

1.11

 medication

1.06

 medications

1.04

 opioids

1.01

 prescribed

1.01

 prescription

0.96

 medicines

0.95

 medicine

0.92

 prescriptions

0.90

Activations Density 0.027%

phrases related to medical prescriptions or prescribing behaviors

terms related to the prescription of medications

No Comments

No Known Activations