INDEX

Explanations

references to the term "Lost"

oai_token-act-pair · gpt-3.5-turbo

the word "Lost" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

enegger

-0.98

utical

-0.85

lication

-0.72

utic

-0.70

OPLE

-0.70

kson

-0.67

resent

-0.67

issance

-0.65

 populated

-0.65

heet

-0.65

POSITIVE LOGITS

 Password

0.87

pedia

0.83

Voy

0.80

 Odyssey

0.80

 Orbit

0.80

 Lost

0.80

 Souls

0.78

 Lives

0.76

 Survivor

0.73

 Memories

0.73

Activations Density 0.017%

references to the term "Lost"

the word "Lost" in various contexts

No Comments

No Known Activations