INDEX

Explanations

periods at the end of sentences

oai_token-act-pair · gpt-3.5-turbo

end punctuation marks

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

 personality

-0.74

 unex

-0.66

 disemb

-0.66

unts

-0.65

 pocket

-0.65

 clos

-0.65

 pillar

-0.63

 involuntary

-0.63

tyr

-0.63

 utter

-0.62

POSITIVE LOGITS

 Unfortunately

1.40

 Ideally

1.36

 Instead

1.17

 Otherwise

1.13

 Specifically

1.13

 Fortunately

1.11

 Luckily

1.09

 Sadly

1.08

 Doing

1.06

But

1.04

Activations Density 0.523%

periods at the end of sentences

end punctuation marks

No Comments

No Known Activations