INDEX

Explanations

words related to websites in a text

oai_token-act-pair · gpt-3.5-turbo

references to websites

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atta

-0.76

 captain

-0.72

 unit

-0.71

 description

-0.71

lander

-0.70

 equation

-0.69

iler

-0.68

 system

-0.67

 piece

-0.64

 module

-0.64

POSITIVE LOGITS

 websites

2.82

 sites

1.93

 blogs

1.78

 Webs

1.72

sites

1.68

 databases

1.68

 Sites

1.62

 directories

1.61

 URLs

1.61

 organisations

1.61

Activations Density 0.056%

words related to websites in a text

references to websites

No Comments

No Known Activations