INDEX

Explanations

terminology 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.80

 Tate

-0.76

 Philips

-0.71

 Carbuncle

-0.67

 Seasons

-0.66

Eco

-0.64

 Wast

-0.62

emonic

-0.62

 Remastered

-0.62

hiba

-0.61

POSITIVE LOGITS

 enforcement

1.39

suit

1.25

enforcement

1.18

makers

1.16

lessness

1.16

breakers

1.14

 abiding

1.10

 Enforcement

1.10

suits

1.10

breaker

1.08

Activations Density 0.044%

terminology related to law enforcement

terms related to law enforcement

No Comments

No Known Activations