INDEX

Explanations

phrases or words indicating possession or ownership

oai_token-act-pair · gpt-3.5-turbo

the end of text tokens or text delimiters

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

 Leilan

-0.47

 Lauder

-0.46

Nev

-0.46

 Rounds

-0.45

 Tours

-0.45

 Prior

-0.44

Pwr

-0.44

 Nutrition

-0.43

 Marian

-0.43

 Pike

-0.43

POSITIVE LOGITS

selves

0.75

pecially

0.71

ustainable

0.70

lightly

0.69

uddenly

0.68

outhern

0.67

etheless

0.67

theless

0.66

outheast

0.64

omew

0.63

Activations Density 0.299%

phrases or words indicating possession or ownership

the end of text tokens or text delimiters

No Comments

No Known Activations