INDEX

Explanations

references to titles, such as movies or books, ending with a punctuation mark

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation, indicating the completion of thoughts or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

izoph

-0.64

 undet

-0.62

 defe

-0.61

 disemb

-0.60

 footing

-0.59

 monop

-0.58

ikuman

-0.58

 unch

-0.58

ozo

-0.57

 predec

-0.57

POSITIVE LOGITS

 Additionally

0.96

 Moreover

0.94

 Needless

0.93

 Furthermore

0.92

 Such

0.90

 Similarly

0.89

 Likewise

0.85

 Meanwhile

0.85

 Naturally

0.83

 Their

0.83

Activations Density 1.086%

references to titles, such as movies or books, ending with a punctuation mark

sentence-ending punctuation, indicating the completion of thoughts or statements

No Comments

No Known Activations