INDEX

Explanations

phrases related to actions being attempted or completed

oai_token-act-pair · gpt-3.5-turbo

special characters or unusual symbols in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Marble

-0.80

 Manhattan

-0.78

 decomp

-0.76

isode

-0.73

 Nebula

-0.72

 Voyager

-0.72

 Staten

-0.71

 Appalachian

-0.69

 Moose

-0.68

 tornado

-0.68

POSITIVE LOGITS

£

1.01

Asia

0.97

Muslims

0.94

¹

0.92

taboola

0.92

¬

0.91

į

0.87

ISIS

0.86

AFP

0.86

Iraq

0.85

Activations Density 0.388%

phrases related to actions being attempted or completed

special characters or unusual symbols in the text

No Comments

No Known Activations