INDEX

Explanations

terms related to background checks, particularly in the context of legal, security, and safety measures

oai_token-act-pair · gpt-3.5-turbo

terms related to background checks and security vetting processes

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

NK

-0.82

rising

-0.75

Church

-0.74

Corn

-0.73

iev

-0.71

temp

-0.70

Lord

-0.70

joy

-0.69

jac

-0.69

quit

-0.68

POSITIVE LOGITS

 troopers

0.91

 audits

0.87

 procedures

0.86

 screenings

0.86

 checks

0.85

 requirements

0.83

 applicants

0.80

 dossier

0.80

 examinations

0.80

essee

0.78

Activations Density 0.032%

terms related to background checks, particularly in the context of legal, security, and safety measures

terms related to background checks and security vetting processes

No Comments

No Known Activations