INDEX

Explanations

terms related to law enforcement

oai_token-act-pair · gpt-3.5-turbo

terms related to law enforcement

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

xit

-0.82

 Carbuncle

-0.76

 Tate

-0.72

 Philips

-0.70

 Remastered

-0.70

 Seasons

-0.68

 Flavoring

-0.65

emonic

-0.64

 Cinnamon

-0.64

Dak

-0.63

POSITIVE LOGITS

 enforcement

1.42

suit

1.30

enforcement

1.19

suits

1.16

lessness

1.13

 Enforcement

1.09

makers

1.09

 abiding

1.08

breakers

1.08

breaker

1.02

Activations Density 0.041%

terms related to law enforcement

terms related to law enforcement

No Comments

No Known Activations