INDEX

Explanations

years from historical events

oai_token-act-pair · gpt-3.5-turbo

specific years, particularly those in the 1700s

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

EStreamFrame

-0.77

 undermin

-0.68

anooga

-0.67

 newcom

-0.67

ļéĨĴ

-0.67

andum

-0.65

 satell

-0.64

 explan

-0.64

ĺħ

-0.63

EStream

-0.62

POSITIVE LOGITS

1.57

1.56

1.55

1.54

1.53

Activations Density 0.043%

years from historical events

specific years, particularly those in the 1700s

No Comments

No Known Activations