INDEX

Explanations

dates and time intervals

oai_token-act-pair · gpt-3.5-turbo

references to specific dates or years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĤ´ãĥ³

-0.94

rack

-0.77

æ©

-0.73

è£

-0.72

ãĥ¥

-0.72

addin

-0.72

Third

-0.66

minster

-0.64

¬¼

-0.64

odox

-0.62

POSITIVE LOGITS

 however

0.66

 whenever

0.62

 subscribers

0.60

 Patricia

0.59

 excluding

0.57

 whichever

0.56

geries

0.55

 unless

0.55

 respectively

0.55

]"

0.55

Activations Density 0.180%

dates and time intervals

references to specific dates or years

No Comments

No Known Activations