INDEX

Explanations

sentences ending with a period or quotation mark followed by a high activation value

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 harness

-0.83

 tremend

-0.80

 endeav

-0.76

ĪĴ

-0.71

 instinct

-0.70

 horrend

-0.69

 utter

-0.69

plet

-0.69

lov

-0.69

ãĤ¤ãĥĪ

-0.69

POSITIVE LOGITS

 Lastly

1.26

 Related

1.23

<|endoftext|>

1.21

 Meanwhile

1.20

 Finally

1.15

 Another

1.12

Meanwhile

1.11

 Others

1.10

 Asked

1.09

 Additionally

1.09

Activations Density 0.496%

sentences ending with a period or quotation mark followed by a high activation value

sentence-ending punctuation

No Known Activations