INDEX

Explanations

references to specific entities or locations preceded by "The"

oai_token-act-pair · gpt-3.5-turbo

the word "The" at the beginning of sentences or clauses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

\<

-0.86

earch

-0.76

âĨĳ

-0.74

GPU

-0.73

.</

-0.73

pload

-0.72

ÏĢ

-0.71

Conclusion

-0.70

FK

-0.70

POSITIVE LOGITS

resa

1.16

 latest

1.04

odore

1.04

 revelation

0.97

 announcement

0.96

 venerable

0.95

oret

0.91

 Associated

0.87

 Huffington

0.86

 sudden

0.84

Activations Density 0.253%

references to specific entities or locations preceded by "The"

the word "The" at the beginning of sentences or clauses

No Comments

No Known Activations