INDEX

Explanations

references to past actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases related to personal experiences and memories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Result

-0.81

 Conclusion

-0.80

 Effect

-0.75

bold

-0.73

 infographic

-0.72

 Congratulations

-0.71

DNA

-0.70

 precedent

-0.70

NOW

-0.69

proven

-0.68

POSITIVE LOGITS

 mornings

1.19

 dinners

1.18

 evenings

1.17

 weekends

1.16

 nights

1.10

 outings

1.08

 chores

1.07

 babys

1.06

 meals

1.04

 trips

1.01

Activations Density 0.634%

references to past actions or events

phrases related to personal experiences and memories

No Comments

No Known Activations