INDEX

Explanations

terms related to algorithms

oai_token-act-pair · gpt-3.5-turbo

references to algorithms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-0.81

shirt

-0.78

ership

-0.77

lihood

-0.71

shirts

-0.68

igi

-0.67

Dak

-0.67

 Wond

-0.66

Lago

-0.66

mares

-0.65

POSITIVE LOGITS

 algorithms

1.16

ically

1.13

 algorithm

1.04

gorithm

0.89

 optimization

0.87

 implementations

0.83

atically

0.81

gorith

0.79

 algorith

0.78

agically

0.77

Activations Density 0.022%

terms related to algorithms

references to algorithms in various contexts

No Comments

No Known Activations