INDEX

Explanations

terms related to different parts of a system, such as compartments, stacks, screens, tunnels, and pipes

oai_token-act-pair · gpt-3.5-turbo

technical terms related to computer systems and interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hiro

-0.66

ivas

-0.65

Southern

-0.62

Ô

-0.61

PAC

-0.61

paren

-0.60

Summer

-0.59

Spring

-0.59

çİĭ

-0.58

hi

-0.58

POSITIVE LOGITS

 itself

0.83

 hierarchy

0.80

 area

0.77

 interface

0.74

 aisle

0.74

(/

0.73

 entrance

0.73

 drawer

0.72

ousel

0.71

 window

0.71

Activations Density 0.317%

terms related to different parts of a system, such as compartments, stacks, screens, tunnels, and pipes

technical terms related to computer systems and interfaces

No Comments

No Known Activations