INDEX

Explanations

sentences or phrases referencing specific sections or products within a website

oai_token-act-pair · gpt-3.5-turbo

complex numerical data and analysis related to business metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 inaug

-0.78

 sacked

-0.70

illance

-0.70

 destined

-0.69

 cartel

-0.68

 sovereign

-0.68

 himself

-0.67

 tagged

-0.66

 herself

-0.65

 gang

-0.65

POSITIVE LOGITS

Example

1.26

Learn

1.22

Examples

1.18

Additionally

1.14

Therefore

1.11

Avoid

1.11

Different

1.10

Consider

1.08

Furthermore

1.08

Conclusion

1.06

Activations Density 0.660%

sentences or phrases referencing specific sections or products within a website

complex numerical data and analysis related to business metrics

No Comments

No Known Activations