INDEX

Explanations

terms related to a specific healthcare policy named "ObamaCare"

oai_token-act-pair · gpt-3.5-turbo

references to the ObamaCare legislation and related healthcare terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ifying

-0.92

antes

-0.88

adoes

-0.86

iddles

-0.86

iless

-0.84

ified

-0.84

arians

-0.82

ier

-0.81

flies

-0.81

ifier

-0.81

POSITIVE LOGITS

Ħ¢

1.01

ORPG

0.76

xia

0.69

eals

0.68

hovah

0.66

0.65

ï¸ı

0.65

ments

0.63

 cand

0.62

lli

0.62

Activations Density 0.054%

terms related to a specific healthcare policy named "ObamaCare"

references to the ObamaCare legislation and related healthcare terms

No Comments

No Known Activations