INDEX

Explanations

dates mentioned in proximity to specific events or occurrences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

<?

-0.80

behind

-0.72

asonic

-0.72

raised

-0.72

ARI

-0.72

reau

-0.71

among

-0.70

 largeDownload

-0.69

è¦

-0.68

 countered

-0.67

POSITIVE LOGITS

 deadline

1.30

 onset

1.26

 expiration

1.19

 arrival

1.18

 inauguration

1.17

 announcement

1.12

 advent

1.09

 election

1.09

 conclusion

1.06

 holidays

1.04

Activations Density 0.121%

dates mentioned in proximity to specific events or occurrences

occurrences of the word "the."

No Comments

No Known Activations