INDEX

Explanations

abbreviations related to various units of measurement

oai_token-act-pair · gpt-3.5-turbo

terms related to measurements and quantities in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cecil

-0.66

 Ragnarok

-0.65

Bir

-0.63

 Metatron

-0.63

 Pirates

-0.62

 Sailor

-0.60

Fu

-0.60

 Ridley

-0.60

 Aval

-0.60

 Odin

-0.59

POSITIVE LOGITS

 apiece

1.13

 increments

1.04

Hz

0.93

poons

0.88

illion

0.87

ilion

0.87

EDT

0.86

elsius

0.85

renheit

0.82

imeter

0.79

Activations Density 0.256%

abbreviations related to various units of measurement

terms related to measurements and quantities in data

No Comments

No Known Activations