INDEX

Explanations

keywords related to algorithms

oai_token-act-pair · gpt-3.5-turbo

references to algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

joy

-0.71

ning

-0.70

nd

-0.68

 Pilgrim

-0.67

shirt

-0.66

Dak

-0.64

nen

-0.63

inelli

-0.63

mare

-0.63

ership

-0.63

POSITIVE LOGITS

 algorithms

1.40

 algorithm

1.40

gorithm

1.14

 algorith

1.03

 guiActiveUn

0.93

 resil

0.91

 optimization

0.90

ically

0.85

 eleph

0.85

gorith

0.84

Activations Density 0.009%

keywords related to algorithms

references to algorithms

No Comments

No Known Activations