INDEX

Explanations

locations or buildings and specific terms or phrases identified as important within a given context

oai_token-act-pair · gpt-3.5-turbo

terms related to main topics or key points in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ïī

-0.81

ifice

-0.78

adr

-0.74

 damned

-0.72

tered

-0.72

 somehow

-0.71

onement

-0.68

Naz

-0.67

emaker

-0.66

livion

-0.66

POSITIVE LOGITS

 Features

1.49

 Facts

1.45

 Examples

1.44

 Results

1.44

 Thoughts

1.44

 Sources

1.41

 Coverage

1.41

 Highlights

1.41

 Comments

1.40

 References

1.39

Activations Density 0.186%

locations or buildings and specific terms or phrases identified as important within a given context

terms related to main topics or key points in a document

No Comments

No Known Activations