INDEX

Explanations

legal and judicial terms

oai_token-act-pair · gpt-3.5-turbo

references to sentences and their severity in the context of legal penalties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

BLIC

-0.99

sie

-0.95

rous

-0.81

chio

-0.75

ikarp

-0.75

aucuses

-0.73

NetMessage

-0.73

sylv

-0.73

flush

-0.73

atform

-0.71

POSITIVE LOGITS

 sentences

1.13

 sentence

1.02

 Guant

0.85

 Guantanamo

0.83

 sentencing

0.81

 probation

0.79

 summ

0.73

 uttered

0.73

 prison

0.72

 inmates

0.71

Activations Density 0.025%

legal and judicial terms

references to sentences and their severity in the context of legal penalties

No Comments

No Known Activations