INDEX

Explanations

words 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

-0.80

nen

-0.77

hold

-0.71

lus

-0.71

Lago

-0.71

lv

-0.70

lihood

-0.69

igi

-0.68

ership

-0.68

ning

-0.67

POSITIVE LOGITS

 algorithms

1.28

 algorithm

1.18

gorithm

0.93

ically

0.91

 guiActiveUn

0.87

 algorith

0.84

 optimization

0.84

gorith

0.82

AES

0.80

 implementations

0.78

Activations Density 0.012%

words related to algorithms

references to algorithms

No Comments

No Known Activations