INDEX

Explanations

evidence of medical examinations and investigations

oai_token-act-pair · gpt-3.5-turbo

references to autopsies and forensic medical examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

campaign

-0.85

rising

-0.77

 freel

-0.74

 inertia

-0.74

channelAvailability

-0.73

=]

-0.71

 piracy

-0.70

imeo

-0.68

ateful

-0.67

escape

-0.67

POSITIVE LOGITS

ysis

1.26

 examination

1.24

 examinations

1.20

 scan

1.16

 scans

1.15

 autopsy

1.15

MRI

1.14

 tests

1.12

 exam

1.07

 Examination

1.06

Activations Density 0.278%

evidence of medical examinations and investigations

references to autopsies and forensic medical examinations

No Comments

No Known Activations