INDEX

Explanations

references to algorithms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "algorithm."

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

ership

-0.73

hold

-0.71

joy

-0.71

lihood

-0.70

Pel

-0.69

irts

-0.69

shirt

-0.68

Lago

-0.67

gets

-0.65

birth

-0.65

POSITIVE LOGITS

 algorithms

1.20

 algorithm

1.07

ically

0.94

gorithm

0.92

 optimization

0.86

gorith

0.81

matically

0.80

 guiActiveUn

0.79

andom

0.75

agically

0.75

Activations Density 0.008%

references to algorithms

occurrences of the word "algorithm."

No Comments

No Known Activations