INDEX

Explanations

terms related to healthcare policy, particularly the Affordable Care Act

oai_token-act-pair · gpt-3.5-turbo

mentions of the Affordable Care Act

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

*/(

-0.80

ondon

-0.78

nir

-0.78

yss

-0.77

ifling

-0.77

govtrack

-0.76

stro

-0.75

Merc

-0.70

REDACTED

-0.70

uj

-0.69

POSITIVE LOGITS

amacare

0.93

 Affordable

0.84

 Advantage

0.78

 Housing

0.76

ordable

0.75

 Care

0.72

 healthcare

0.69

 ObamaCare

0.68

 Savings

0.66

 Healthcare

0.66

Activations Density 0.009%

terms related to healthcare policy, particularly the Affordable Care Act

mentions of the Affordable Care Act

No Comments

No Known Activations