INDEX

Explanations

phrases related to laws, rules, and principles

oai_token-act-pair · gpt-3.5-turbo

references to rules, laws, or principles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LY

-0.85

 istg

-0.83

ucci

-0.76

Enlarge

-0.76

Ô

-0.75

OV

-0.72

quickShipAvailable

-0.71

by

-0.69

BU

-0.68

POSITIVE LOGITS

our

0.75

 darkness

0.74

 morality

0.74

 decency

0.73

 civilization

0.73

 everyday

0.71

 persuasion

0.70

 civilisation

0.69

 various

0.68

 hardship

0.67

Activations Density 0.237%

phrases related to laws, rules, and principles

references to rules, laws, or principles

No Comments

No Known Activations