INDEX

Explanations

information sources or attributions in a text

oai_token-act-pair · gpt-3.5-turbo

citations or references to sources

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 monster

-0.71

 choice

-0.70

 mood

-0.70

 turn

-0.68

 pain

-0.68

 affair

-0.66

act

-0.66

 performance

-0.66

 accent

-0.66

 perfectly

-0.65

POSITIVE LOGITS

Sources

4.27

 Sources

2.44

References

2.13

Source

1.75

 sources

1.51

ources

1.48

Resources

1.39

Appearances

1.38

Images

1.36

SOURCE

1.35

Activations Density 0.010%

information sources or attributions in a text

citations or references to sources

No Comments

No Known Activations