INDEX

Explanations

phrases containing the word "Things"

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "Things" followed by various topics or issues

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 suite

-0.66

 sponsor

-0.65

UAL

-0.65

 blast

-0.64

mas

-0.64

 permit

-0.63

adel

-0.62

cum

-0.61

 circ

-0.61

 scan

-0.60

POSITIVE LOGITS

 Things

3.70

Things

2.92

things

2.40

 things

1.95

 Thing

1.88

 Stuff

1.56

 Everything

1.48

 Something

1.47

Something

1.34

 Moments

1.32

Activations Density 0.011%

phrases containing the word "Things"

the repeated phrase "Things" followed by various topics or issues

No Known Activations