INDEX

Explanations

signs of dialogue with commas followed by an attribute or description

oai_token-act-pair · gpt-3.5-turbo

repetitious phrases or clauses that contribute to sentence structure

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Nasa

-0.76

 Nato

-0.68

 Armageddon

-0.68

 realise

-0.67

NEO

-0.66

 landfill

-0.66

US

-0.65

 realised

-0.64

 Finder

-0.63

 practise

-0.62

POSITIVE LOGITS

âĢ

1.85

Â»

1.41

âĸł

1.39

âĢł

1.36

**

1.34

ãĢ

1.31

1.30

âĹı

1.28

âľ

1.27

Â«

1.27

Activations Density 0.366%

signs of dialogue with commas followed by an attribute or description

repetitious phrases or clauses that contribute to sentence structure

No Comments

No Known Activations