INDEX

Explanations

words associated with providing protection or defense

oai_token-act-pair · gpt-3.5-turbo

references to protective measures or barriers

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Moz

-0.84

 Calvin

-0.78

 Kinder

-0.67

rences

-0.67

Bie

-0.66

CPC

-0.66

 Jobs

-0.65

Von

-0.65

 Recomm

-0.65

omin

-0.64

POSITIVE LOGITS

 shield

3.43

 Shield

3.30

 shields

3.15

Shield

2.90

shield

2.69

 Shields

2.47

 shielding

2.25

 shielded

1.84

 cloak

1.36

 shroud

1.28

Activations Density 0.018%

words associated with providing protection or defense

references to protective measures or barriers

No Known Activations