INDEX

Explanations

words related to medical facilities or clinics

oai_token-act-pair · gpt-3.5-turbo

mentions of clinics, specifically related to healthcare services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lass

-0.72

sum

-0.66

 Marketable

-0.64

lust

-0.64

ãĥĥãĥī

-0.63

lasses

-0.63

stad

-0.63

gest

-0.63

 quot

-0.62

izoph

-0.61

POSITIVE LOGITS

opath

0.87

 clinics

0.83

 specializing

0.82

 clinic

0.82

 pharmacy

0.76

 Clinic

0.75

 stalls

0.74

 pharmacies

0.73

idges

0.72

 attendant

0.72

Activations Density 0.036%

words related to medical facilities or clinics

mentions of clinics, specifically related to healthcare services

No Comments

No Known Activations