INDEX

Explanations

words related to negative actions or situations such as theft, hijacking, and destruction

oai_token-act-pair · gpt-3.5-turbo

terms related to loss, damage, or capture

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

ledge

-0.83

BIT

-0.83

adra

-0.77

armed

-0.74

adan

-0.73

fuck

-0.72

cially

-0.72

apo

-0.72

upuncture

-0.71

notice

-0.70

POSITIVE LOGITS

 carc

0.94

 corpses

0.92

 goods

0.90

 portions

0.84

 souls

0.82

 corpse

0.79

 manuscripts

0.76

 portion

0.76

 assets

0.74

 copies

0.72

Activations Density 0.271%

words related to negative actions or situations such as theft, hijacking, and destruction

terms related to loss, damage, or capture

No Comments

No Known Activations