INDEX

Explanations

references to legal matters

oai_token-act-pair · gpt-3.5-turbo

references to legal matters or the concept of legality

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seasons

-0.86

mble

-0.80

 Tycoon

-0.70

 Decay

-0.70

ochond

-0.69

ritch

-0.68

vae

-0.67

 Velocity

-0.67

 finalists

-0.66

Vaj

-0.66

POSITIVE LOGITS

 enforce

0.89

 obliged

0.82

 obligated

0.82

BuyableInstoreAndOnline

0.81

 compliant

0.81

 authorized

0.81

 sanctioned

0.79

 prohibited

0.77

 ratified

0.76

 licensed

0.76

Activations Density 0.028%

references to legal matters

references to legal matters or the concept of legality

No Comments

No Known Activations