INDEX

Explanations

specific technical terms related to lenses in a camera system

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

lly

-0.77

onge

-0.71

TY

-0.69

currency

-0.69

ansom

-0.67

DAY

-0.66

BY

-0.66

uca

-0.64

DIT

-0.63

lishes

-0.63

POSITIVE LOGITS

 lens

1.11

 lenses

1.11

 flares

1.08

 flare

1.00

linger

0.92

 Lens

0.90

Lens

0.85

 glasses

0.84

 Nikon

0.81

ner

0.80

Activations Density 0.035%

specific technical terms related to lenses in a camera system

No Comments

No Known Activations