INDEX

Explanations

information related to railway infrastructure or projects

oai_token-act-pair · gpt-3.5-turbo

mentions of rail systems or related components

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

ynski

-0.72

endi

-0.70

rell

-0.69

wed

-0.68

cho

-0.67

 weed

-0.67

essler

-0.64

ena

-0.62

worthy

-0.61

tnc

-0.60

POSITIVE LOGITS

 Rail

4.26

Rail

2.89

 rail

2.26

rail

2.18

 Railway

2.07

 railways

1.74

 Railroad

1.58

 rails

1.48

 railway

1.44

 Amtrak

1.30

Activations Density 0.018%

information related to railway infrastructure or projects

mentions of rail systems or related components

No Comments

No Known Activations