INDEX

Explanations

phrases related to time frames, particularly specific durations such as "months" or "years"

oai_token-act-pair · gpt-3.5-turbo

references to time periods, specifically years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Andromeda

-0.71

 Schwarz

-0.68

 Crunch

-0.62

 Sanctuary

-0.62

ãĤ¼ãĤ¦ãĤ¹

-0.62

 Strongh

-0.62

Unc

-0.60

 Halls

-0.59

atro

-0.58

own

-0.58

POSITIVE LOGITS

ago

1.16

 apiece

0.95

undred

0.86

uana

0.83

Ago

0.79

 elapsed

0.76

ilver

0.76

utical

0.76

 olds

0.75

endment

0.75

Activations Density 0.182%

phrases related to time frames, particularly specific durations such as "months" or "years"

references to time periods, specifically years and months

No Comments

No Known Activations