INDEX

Explanations

names of hospitals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific hospitals and medical centers

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

 sheet

-0.82

BOOK

-0.78

lass

-0.74

 sheets

-0.70

lyr

-0.68

 tune

-0.65

lang

-0.63

^^^^

-0.61

NYT

-0.60

 BOOK

-0.60

POSITIVE LOGITS

 Plaza

0.94

 Hospital

0.92

 Patients

0.89

ilitation

0.88

 Clinic

0.84

 Medical

0.81

aceutical

0.79

 Corporation

0.79

 District

0.78

 Simulator

0.78

Activations Density 0.021%

names of hospitals

mentions of specific hospitals and medical centers

No Comments

No Known Activations