INDEX

Explanations

words related to laws and regulations

oai_token-act-pair · gpt-3.5-turbo

regulatory measures and rules related to policies and laws

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

Joy

-0.70

culus

-0.64

asca

-0.63

ovies

-0.61

 Prayer

-0.61

 sensations

-0.61

 Gall

-0.60

else

-0.60

 Donation

-0.60

oom

-0.60

POSITIVE LOGITS

 enforced

1.23

enforcement

1.14

 regulating

1.12

 governs

1.10

 governing

1.09

 promulg

1.09

 regulations

1.08

 enforce

1.08

 prohibiting

1.08

 enforcement

1.01

Activations Density 0.526%

words related to laws and regulations

regulatory measures and rules related to policies and laws

No Comments

No Known Activations