INDEX

Explanations

addresses or locations

oai_token-act-pair · gpt-3.5-turbo

specific locations or addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Analy

-0.67

icter

-0.62

 causation

-0.62

hap

-0.60

âĵĺ

-0.60

 elsewhere

-0.58

ens

-0.58

fal

-0.57

iris

-0.57

Interstitial

-0.56

POSITIVE LOGITS

 Blvd

0.99

illion

0.82

Ave

0.77

 apiece

0.69

eno

0.67

Rd

0.67

elsius

0.64

??

0.63

 acres

0.63

endment

0.63

Activations Density 0.488%

addresses or locations

specific locations or addresses

No Comments

No Known Activations