INDEX

Explanations

phrases related to mathematical or technical discussions, particularly involving calculations, distributions, and processes

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate relationships or connections between concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

meet

-0.82

pees

-0.81

aws

-0.78

å¥³

-0.78

justice

-0.73

ollo

-0.72

itans

-0.72

çīĪ

-0.72

CNN

-0.72

rir

-0.71

POSITIVE LOGITS

 hence

1.40

 therefore

1.34

 consequently

1.33

 thereby

1.29

 thus

1.28

 optionally

1.11

 thence

1.11

 consequ

1.09

 subsequently

1.09

rogens

1.03

Activations Density 0.464%

phrases related to mathematical or technical discussions, particularly involving calculations, distributions, and processes

phrases that indicate relationships or connections between concepts

No Comments

No Known Activations