INDEX

Explanations

phrases related to reflection or conclusion

oai_token-act-pair · gpt-3.5-turbo

phrases that reference time-related reflections or conclusions, particularly "at the end of the day"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

obin

-0.64

phasis

-0.63

etic

-0.62

 Attention

-0.61

orest

-0.60

ort

-0.59

ensitive

-0.57

 corrective

-0.57

rac

-0.56

esthetic

-0.56

POSITIVE LOGITS

day

1.17

DAY

0.96

day

0.80

Day

0.78

days

0.76

 nutshell

0.75

 days

0.74

Day

0.71

åħ

0.69

iHUD

0.66

Activations Density 0.043%

phrases related to reflection or conclusion

phrases that reference time-related reflections or conclusions, particularly "at the end of the day"

No Comments

No Known Activations