INDEX

Explanations

references to versions or updates within a sequence of text

oai_token-act-pair · gpt-3.5-turbo

instances of numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĸļ

-0.73

 occasion

-0.71

htaking

-0.68

 spir

-0.64

 concentrated

-0.62

 lasting

-0.61

 neighb

-0.61

 earthqu

-0.61

 grop

-0.60

 mould

-0.60

POSITIVE LOGITS

References

1.16

rawdownloadcloneembedreportprint

1.13

Conclusion

1.11

Trivia

1.09

Notable

1.07

Acknowled

1.05

Discussion

1.02

Examples

1.01

Features

0.98

Advertisements

0.98

Activations Density 0.224%

references to versions or updates within a sequence of text

instances of numerical data or statistics

No Comments

No Known Activations