INDEX

Explanations

lists of recommendations or strategies

oai_token-act-pair · gpt-3.5-turbo

lists or enumerations of advice, suggestions, or guidelines

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

ebook

-0.79

 Athletic

-0.70

BI

-0.67

eed

-0.65

cffffcc

-0.64

nee

-0.64

vik

-0.64

RTX

-0.63

aukee

-0.62

rights

-0.62

POSITIVE LOGITS

viz

0.86

 apiece

0.80

 totaling

0.78

âĺħ

0.66

 simultaneously

0.63

 sequ

0.63

 consecut

0.62

âĦ¢:

0.60

 interconnected

0.60

å°Ĩ

0.58

Activations Density 0.213%

lists of recommendations or strategies

lists or enumerations of advice, suggestions, or guidelines

No Comments

No Known Activations