INDEX

Explanations

phrases related to comparisons or evaluations

oai_token-act-pair · gpt-3.5-turbo

phrases that highlight significant topics or concepts within a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

iture

-0.89

anse

-0.77

ourt

-0.75

heit

-0.72

brance

-0.71

aeus

-0.70

CLE

-0.70

UME

-0.69

.............

-0.68

ablishment

-0.66

POSITIVE LOGITS

 reasons

1.41

 coolest

1.29

 biggest

1.24

 earliest

1.24

 hardest

1.20

 easiest

1.20

 greatest

1.18

 drawbacks

1.18

 strang

1.17

 simplest

1.13

Activations Density 0.078%

phrases related to comparisons or evaluations

phrases that highlight significant topics or concepts within a discussion

No Comments

No Known Activations