INDEX

Explanations

phrases indicating improvement or progress

oai_token-act-pair · gpt-3.5-turbo

terms related to improvements and enhancements

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

 Held

-0.73

eps

-0.71

nai

-0.69

 Bind

-0.69

 Masquerade

-0.68

Pos

-0.65

Dir

-0.65

 unwittingly

-0.63

 Pand

-0.62

plets

-0.62

POSITIVE LOGITS

 improvement

3.84

 Improvement

2.56

 improvements

2.55

improve

2.38

 Improvements

1.95

Improve

1.91

 improved

1.87

 improving

1.86

 enhancement

1.83

 improve

1.69

Activations Density 0.018%

phrases indicating improvement or progress

terms related to improvements and enhancements

No Known Activations