INDEX

Explanations

text sequences that are used for censoring or redacting offensive or inappropriate language

oai_token-act-pair · gpt-3.5-turbo

sequences of asterisks or similar patterns in the text

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

Not in Any Lists

No Comments

Negative Logits

 decl

-0.67

 nitrogen

-0.62

 temporal

-0.61

 neutrality

-0.59

quickShipAvailable

-0.59

 reimb

-0.59

Geo

-0.59

ãĤ·ãĥ£

-0.58

 accompanying

-0.57

ular

-0.57

POSITIVE LOGITS

***

3.98

****

3.27

*****

3.13

**

2.89

***

2.63

********

2.55

************

2.30

 ****

2.14

****************

2.02

********************************

2.00

Activations Density 0.017%

text sequences that are used for censoring or redacting offensive or inappropriate language

sequences of asterisks or similar patterns in the text

No Comments

No Known Activations