INDEX

Explanations

percentages or statistical figures

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 philos

-0.75

 sourcing

-0.69

 parach

-0.68

 distilled

-0.67

 snowball

-0.66

 pudding

-0.65

 stocking

-0.65

 recycling

-0.64

 masc

-0.64

 stim

-0.64

POSITIVE LOGITS

1.37

1.33

1.32

1.31

1.27

1.25

Activations Density 0.067%

percentages or statistical figures

No Comments

No Known Activations