INDEX

Explanations

terms related to legal matters and regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to legality or legal concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Seym

-0.69

 Canaver

-0.66

 looph

-0.58

Synopsis

-0.58

 Bris

-0.56

amina

-0.56

 Bowen

-0.55

reb

-0.52

oret

-0.51

wealth

-0.51

POSITIVE LOGITS

 would

1.06

 becomes

1.05

 implies

1.01

 tends

1.01

 ensued

1.00

 became

0.99

 could

0.98

was

0.98

 awaits

0.97

 ensures

0.96

Activations Density 0.883%

terms related to legal matters and regulations

terms related to legality or legal concepts

No Comments

No Known Activations