INDEX

Explanations

sentences ending with a full stop

oai_token-act-pair · gpt-3.5-turbo

sentences or phrases that indicate conclusions or final remarks

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

 imperson

-0.79

 snowball

-0.72

 dich

-0.72

 buggy

-0.72

 attent

-0.71

 utter

-0.71

 negativity

-0.71

 bashing

-0.71

 belly

-0.71

 dispar

-0.71

POSITIVE LOGITS

 Alternatively

1.44

 Ideally

1.37

 Currently

1.34

 Otherwise

1.32

 Depending

1.31

 Already

1.26

 Additionally

1.22

 Moreover

1.21

 Furthermore

1.16

 Assuming

1.16

Activations Density 0.532%

sentences ending with a full stop

sentences or phrases that indicate conclusions or final remarks

No Comments

No Known Activations