INDEX

Explanations

keywords related to technology components or parts, often in the context of automation or assembly

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

standing

-0.78

kers

-0.75

stretched

-0.72

 Predators

-0.70

bies

-0.68

 Croat

-0.68

ipeg

-0.67

ker

-0.65

berman

-0.65

uca

-0.65

POSITIVE LOGITS

 components

0.92

 parts

0.87

 component

0.86

 thereof

0.86

 Components

0.82

 subsystem

0.79

onents

0.78

 Component

0.78

iation

0.77

 additive

0.73

Activations Density 0.021%

keywords related to technology components or parts, often in the context of automation or assembly

No Comments

No Known Activations