INDEX

Explanations

phrases related to healthcare and government policies around healthcare

oai_token-act-pair · gpt-3.5-turbo

references to health care policies and proposals

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

sov

-0.91

pload

-0.87

Zup

-0.86

inous

-0.82

Äĩ

-0.80

selage

-0.79

ocular

-0.77

vous

-0.75

gaard

-0.74

opal

-0.73

POSITIVE LOGITS

 necessities

0.85

 commodities

0.81

 empowerment

0.81

 childbirth

0.79

 welf

0.79

 vouchers

0.74

ascript

0.74

 nursing

0.73

 vocational

0.72

 subsidies

0.72

Activations Density 0.720%

phrases related to healthcare and government policies around healthcare

references to health care policies and proposals

No Comments

No Known Activations