INDEX

Explanations

references to algorithms

oai_token-act-pair · gpt-3.5-turbo

mentions of algorithms and their applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

joy

-0.81

hold

-0.71

ership

-0.70

shirt

-0.68

nd

-0.67

ning

-0.66

nen

-0.66

Lago

-0.66

gets

-0.65

igi

-0.64

POSITIVE LOGITS

 algorithms

1.34

 algorithm

1.27

gorithm

1.01

ically

0.90

 optimization

0.90

 algorith

0.89

gorith

0.87

 guiActiveUn

0.82

matically

0.82

 eleph

0.80

Activations Density 0.007%

references to algorithms

mentions of algorithms and their applications

No Comments

No Known Activations