INDEX

Explanations

words related to laws and legal concepts

oai_token-act-pair · gpt-3.5-turbo

references to legal concepts and laws

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Dak

-0.73

 Cros

-0.69

vae

-0.69

 Scion

-0.68

Mul

-0.64

 Remastered

-0.62

attery

-0.62

icker

-0.60

ched

-0.59

 Tate

-0.58

POSITIVE LOGITS

 enforcement

1.14

lessness

1.06

suit

1.00

 Enforcement

0.96

suits

0.94

enforcement

0.93

 abiding

0.93

esian

0.88

breakers

0.85

yer

0.83

Activations Density 0.042%

words related to laws and legal concepts

references to legal concepts and laws

No Comments

No Known Activations