INDEX

Explanations

references to locations or regions with 'Strip' in their name

oai_token-act-pair · gpt-3.5-turbo

references to "Strip," particularly in a geographical context

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

otin

-0.70

AD

-0.70

ability

-0.67

amy

-0.63

ag

-0.63

ka

-0.61

AD

-0.61

om

-0.60

tea

-0.59

able

-0.58

POSITIVE LOGITS

 Strip

4.48

strip

2.11

 strip

2.02

 Stri

1.40

 strips

1.38

 stripes

1.22

 striped

1.11

 stripe

1.09

stri

0.95

 Wasteland

0.95

Activations Density 0.015%

references to locations or regions with 'Strip' in their name

references to "Strip," particularly in a geographical context

No Comments

No Known Activations