INDEX

Explanations

phrases related to specific information or locations within a longer text

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation and specific phrases indicative of lists or separators in text

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

é¾įåĸļå£«

-0.85

merce

-0.69

undred

-0.69

Initialized

-0.67

iffe

-0.65

\\\\

-0.63

bilt

-0.63

ucci

-0.63

ãĤ´ãĥ³

-0.62

zn

-0.61

POSITIVE LOGITS

etc

0.67

 Shutterstock

0.63

 clipboard

0.62

 Foley

0.55

 buoy

0.55

ensis

0.55

aka

0.54

eh

0.53

yahoo

0.53

 whereby

0.51

Activations Density 0.866%

phrases related to specific information or locations within a longer text

instances of punctuation and specific phrases indicative of lists or separators in text

No Comments

No Known Activations