INDEX

Explanations

mentions of encryption-related terms

oai_token-act-pair · gpt-3.5-turbo

references to encryption and related security protocols

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

lore

-0.79

llo

-0.77

gal

-0.76

 Fernand

-0.73

enez

-0.69

anan

-0.69

gaard

-0.69

uko

-0.67

 Phelps

-0.67

borough

-0.67

POSITIVE LOGITS

ryption

1.39

rypted

1.21

 encryption

1.20

encrypted

1.18

 encrypt

1.18

 encrypted

1.17

AES

1.07

 cryptography

1.05

 cryptographic

1.04

 handshake

1.04

Activations Density 0.080%

mentions of encryption-related terms

references to encryption and related security protocols

No Comments

No Known Activations