INDEX

Explanations

unstructured and unrelated sequences of characters or symbols

oai_token-act-pair · gpt-3.5-turbo

punctuation and formatting markers in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lobbied

-0.74

 intervened

-0.74

 appoint

-0.74

 choking

-0.71

 divest

-0.71

 answ

-0.71

 uncond

-0.71

 counsel

-0.70

 probation

-0.70

 amnesty

-0.69

POSITIVE LOGITS

Screenshot

1.15

Courtesy

1.10

Conclusion

1.09

Figure

1.08

Notice

1.08

Below

1.05

Gallery

1.01

Video

1.00

Legend

1.00

Ingredients

0.99

Activations Density 0.460%

unstructured and unrelated sequences of characters or symbols

punctuation and formatting markers in the text

No Comments

No Known Activations